@openai/codex-security 0.1.11 → 0.1.13
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +195 -49
- package/_bundled_plugin/.codex-plugin/plugin.json +1 -1
- package/_bundled_plugin/.mcp.json +2 -0
- package/_bundled_plugin/examples/completed-scan/coverage.json +1 -1
- package/_bundled_plugin/examples/completed-scan/scan-manifest.json +2 -2
- package/_bundled_plugin/mcp/server.mjs.br.part-000 +0 -0
- package/_bundled_plugin/mcp/server.mjs.br.part-001 +0 -0
- package/_bundled_plugin/preflight/capability-profiles.toml +1 -34
- package/_bundled_plugin/references/config-preflight.md +11 -13
- package/_bundled_plugin/references/core-scan.md +94 -0
- package/_bundled_plugin/references/final-report.md +6 -6
- package/_bundled_plugin/references/scan-artifacts.md +15 -14
- package/_bundled_plugin/references/scan-prologue.md +27 -0
- package/_bundled_plugin/schemas/tools/deep-reducer.schema.json +1 -106
- package/_bundled_plugin/scripts/config_preflight.py +40 -3
- package/_bundled_plugin/scripts/deep_scan_config.py +8 -5
- package/_bundled_plugin/scripts/deep_scan_workbench.py +103 -35
- package/_bundled_plugin/scripts/finalize_scan_contract.py +29 -17
- package/_bundled_plugin/scripts/finding_preview.py +122 -6
- package/_bundled_plugin/scripts/generate_in_scope_files.py +39 -17
- package/_bundled_plugin/scripts/generate_rank_input.py +21 -3
- package/_bundled_plugin/scripts/normalize_candidates.py +5 -5
- package/_bundled_plugin/scripts/report_projection.py +1 -19
- package/_bundled_plugin/scripts/workbench_cli.py +4 -0
- package/_bundled_plugin/scripts/workbench_db.py +280 -29
- package/_bundled_plugin/scripts/workbench_progress.py +0 -5
- package/_bundled_plugin/scripts/workbench_scan_usage.py +69 -8
- package/_bundled_plugin/scripts/workbench_schema.py +41 -20
- package/_bundled_plugin/skills/attack-path-analysis/SKILL.md +8 -11
- package/_bundled_plugin/skills/deep-security-scan/SKILL.md +24 -110
- package/_bundled_plugin/skills/security-scan/SKILL.md +5 -88
- package/_bundled_plugin/skills/threat-model/SKILL.md +4 -2
- package/_bundled_plugin/skills/track-findings/SKILL.md +1 -1
- package/_bundled_plugin/skills/triage-finding/SKILL.md +5 -6
- package/_bundled_plugin/skills/triage-finding/references/github-rest-intake.md +6 -7
- package/_bundled_plugin/skills/validation/SKILL.md +9 -12
- package/_bundled_plugin/skills/vulnerability-writeup/SKILL.md +3 -2
- package/_bundled_plugin/skills/vulnerability-writeup/references/report-format.md +1 -1
- package/dist/api.d.ts +1 -0
- package/dist/api.d.ts.map +1 -1
- package/dist/api.js +195 -59
- package/dist/api.js.map +1 -1
- package/dist/bulk-scan-discovery.d.ts +5 -1
- package/dist/bulk-scan-discovery.d.ts.map +1 -1
- package/dist/bulk-scan-discovery.js +38 -9
- package/dist/bulk-scan-discovery.js.map +1 -1
- package/dist/cli.d.ts +9 -3
- package/dist/cli.d.ts.map +1 -1
- package/dist/cli.js +764 -60
- package/dist/cli.js.map +1 -1
- package/dist/config.d.ts.map +1 -1
- package/dist/config.js +1 -0
- package/dist/config.js.map +1 -1
- package/dist/contract.d.ts +12 -0
- package/dist/contract.d.ts.map +1 -1
- package/dist/contract.js +30 -2
- package/dist/contract.js.map +1 -1
- package/dist/cost.d.ts.map +1 -1
- package/dist/cost.js +10 -1
- package/dist/cost.js.map +1 -1
- package/dist/index.d.ts +2 -0
- package/dist/index.d.ts.map +1 -1
- package/dist/index.js +1 -0
- package/dist/index.js.map +1 -1
- package/dist/knowledge-base.d.ts.map +1 -1
- package/dist/knowledge-base.js +10 -3
- package/dist/knowledge-base.js.map +1 -1
- package/dist/multiscan.d.ts +1 -0
- package/dist/multiscan.d.ts.map +1 -1
- package/dist/multiscan.js +77 -18
- package/dist/multiscan.js.map +1 -1
- package/dist/publication-events.d.ts +16 -0
- package/dist/publication-events.d.ts.map +1 -0
- package/dist/publication-events.js +141 -0
- package/dist/publication-events.js.map +1 -0
- package/dist/publication-store.d.ts +5 -0
- package/dist/publication-store.d.ts.map +1 -0
- package/dist/publication-store.js +102 -0
- package/dist/publication-store.js.map +1 -0
- package/dist/publication.d.ts +27 -0
- package/dist/publication.d.ts.map +1 -0
- package/dist/publication.js +207 -0
- package/dist/publication.js.map +1 -0
- package/dist/publish.d.ts +77 -0
- package/dist/publish.d.ts.map +1 -0
- package/dist/publish.js +748 -0
- package/dist/publish.js.map +1 -0
- package/dist/runtime.d.ts.map +1 -1
- package/dist/runtime.js +15 -44
- package/dist/runtime.js.map +1 -1
- package/dist/scan-dashboard.d.ts +7 -1
- package/dist/scan-dashboard.d.ts.map +1 -1
- package/dist/scan-dashboard.js +86 -20
- package/dist/scan-dashboard.js.map +1 -1
- package/dist/scan-logs.d.ts +2 -0
- package/dist/scan-logs.d.ts.map +1 -1
- package/dist/scan-logs.js +97 -37
- package/dist/scan-logs.js.map +1 -1
- package/dist/targets.d.ts.map +1 -1
- package/dist/targets.js +20 -11
- package/dist/targets.js.map +1 -1
- package/dist/trusted-executable.js +1 -1
- package/dist/trusted-executable.js.map +1 -1
- package/dist/version.d.ts +3 -3
- package/dist/version.d.ts.map +1 -1
- package/dist/version.js +6 -4
- package/dist/version.js.map +1 -1
- package/package.json +5 -4
- package/_bundled_plugin/references/shared-hard-rules.md +0 -15
- package/_bundled_plugin/scripts/validate_report_format.py +0 -138
- package/_bundled_plugin/skills/security-scan/references/repository-wide-scan.md +0 -33
package/README.md
CHANGED
|
@@ -16,10 +16,11 @@ npx @openai/codex-security --version
|
|
|
16
16
|
```
|
|
17
17
|
|
|
18
18
|
The package supports macOS, Linux, and Windows and requires Node.js 22.13.0 or
|
|
19
|
-
later in the 22.x release line, Node.js 24.x, or Node.js 26.x.
|
|
20
|
-
|
|
21
|
-
|
|
22
|
-
`
|
|
19
|
+
later in the 22.x release line, Node.js 24.x, or Node.js 26.x. Scans, bulk
|
|
20
|
+
scans, exports, scan history, and saved findings also require Python 3.10 or
|
|
21
|
+
later. Python 3.10 also requires `tomli`. Use `--python` with `scan`,
|
|
22
|
+
`bulk-scan`, or `export`; use `pythonPath` with the SDK. Set `PYTHON` to select
|
|
23
|
+
an interpreter for any Python-backed command.
|
|
23
24
|
|
|
24
25
|
When a newer version is available, the CLI shows the update command for your
|
|
25
26
|
installation method. Set `CODEX_SECURITY_NO_UPDATE_NOTICE=1` to hide the
|
|
@@ -199,6 +200,7 @@ Trusted Access for Cyber. To apply or check your access, visit
|
|
|
199
200
|
## CLI
|
|
200
201
|
|
|
201
202
|
```bash
|
|
203
|
+
npx @openai/codex-security scan
|
|
202
204
|
npx @openai/codex-security scan /path/to/repository
|
|
203
205
|
npx @openai/codex-security scan /path/to/repository --headless
|
|
204
206
|
npx @openai/codex-security scan /path/to/repository --model gpt-5.6-terra
|
|
@@ -217,22 +219,31 @@ npx @openai/codex-security scan /path/to/repository --mode deep --workers 2 --su
|
|
|
217
219
|
npx @openai/codex-security install-hook
|
|
218
220
|
npx @openai/codex-security bulk-scan
|
|
219
221
|
npx @openai/codex-security bulk-scan --model gpt-5.6-terra --effort high
|
|
220
|
-
npx @openai/codex-security bulk-scan --workers 4 --mode deep --max-attempts 3
|
|
222
|
+
npx @openai/codex-security bulk-scan --workers 4 --mode deep --max-attempts 3 --max-cost 25
|
|
221
223
|
npx @openai/codex-security bulk-scan repositories.csv --output-dir /path/outside/repositories/security-scans --workers 4 --knowledge-base /path/to/threat-models --knowledge-base /path/to/architecture.pdf
|
|
222
224
|
npx @openai/codex-security bulk-scan repositories.csv --output-dir /path/outside/repositories/security-scans --scan-prompt-file scan.md --post-scan-prompt-file follow-up.md
|
|
223
225
|
npx @openai/codex-security scans list /path/to/repository
|
|
224
226
|
npx @openai/codex-security scans list --scan-root /path/outside/repository/results
|
|
227
|
+
npx @openai/codex-security scans show
|
|
225
228
|
npx @openai/codex-security scans show SCAN_ID
|
|
229
|
+
npx @openai/codex-security scans logs
|
|
226
230
|
npx @openai/codex-security scans logs SCAN_ID
|
|
231
|
+
npx @openai/codex-security scans rerun
|
|
227
232
|
npx @openai/codex-security scans rerun SCAN_ID
|
|
228
233
|
npx @openai/codex-security scans match PREVIOUS_SCAN_ID CURRENT_SCAN_ID
|
|
229
234
|
npx @openai/codex-security scans match --all
|
|
235
|
+
npx @openai/codex-security scans compare
|
|
236
|
+
npx @openai/codex-security scans compare PREVIOUS_SCAN_ID
|
|
230
237
|
npx @openai/codex-security scans compare PREVIOUS_SCAN_ID CURRENT_SCAN_ID
|
|
238
|
+
npx @openai/codex-security findings
|
|
231
239
|
npx @openai/codex-security findings list /path/to/repository
|
|
232
240
|
npx @openai/codex-security findings false-positive OCCURRENCE_ID --reason "The route already checks permissions"
|
|
241
|
+
npx @openai/codex-security export
|
|
233
242
|
npx @openai/codex-security export /path/outside/repository/results --export-format sarif --output /path/outside/repository/results.sarif
|
|
234
243
|
npx @openai/codex-security export /path/outside/repository/results --export-format csv --output /path/outside/repository/findings.csv
|
|
235
244
|
npx @openai/codex-security export /path/outside/repository/results --export-format json --output /path/outside/repository/findings.json
|
|
245
|
+
npx @openai/codex-security publish scan /path/outside/repository/results --to linear --linear-team TEAM_ID
|
|
246
|
+
npx @openai/codex-security publish scan --to linear --linear-team TEAM_ID
|
|
236
247
|
npx @openai/codex-security validate /path/outside/repository/findings.json "Possible SQL injection in src/query.ts:42"
|
|
237
248
|
npx @openai/codex-security validate "Possible SQL injection" --effort high
|
|
238
249
|
npx @openai/codex-security patch /path/outside/repository/findings.json "Missing authorization check in src/routes.ts:18"
|
|
@@ -256,6 +267,10 @@ directory and any enclosing Git worktree. When SARIF is produced, it is written
|
|
|
256
267
|
to
|
|
257
268
|
`<scan-dir>/exports/results.sarif`.
|
|
258
269
|
|
|
270
|
+
Working-tree snapshots include files from untracked nested Git repositories.
|
|
271
|
+
Initialized submodules must be clean and checked out at the commit recorded by
|
|
272
|
+
the parent repository.
|
|
273
|
+
|
|
259
274
|
Repeat `--knowledge-base PATH` for multiple files or directories; `bulk-scan`
|
|
260
275
|
shares them with every repository. Directories are searched recursively for
|
|
261
276
|
Markdown, text, PDF, and Word (`.docx`) files.
|
|
@@ -317,7 +332,7 @@ mode.
|
|
|
317
332
|
|
|
318
333
|
Scans use `gpt-5.6-sol` with extra-high reasoning effort by default. OpenAI is
|
|
319
334
|
the implied provider. Use `--model gpt-5.6-terra` to switch models and
|
|
320
|
-
`--effort minimal|low|medium|high|xhigh` to set reasoning effort. Repeat
|
|
335
|
+
`--effort minimal|low|medium|high|xhigh|max` to set reasoning effort. Repeat
|
|
321
336
|
`--codex KEY=VALUE` for other Codex settings; existing
|
|
322
337
|
`--codex 'model_reasoning_effort="high"'` overrides remain supported.
|
|
323
338
|
|
|
@@ -328,7 +343,8 @@ configuration. Each scan starts with a private runtime and these Codex
|
|
|
328
343
|
defaults:
|
|
329
344
|
|
|
330
345
|
```toml
|
|
331
|
-
|
|
346
|
+
approval_policy = "never"
|
|
347
|
+
cli_auth_credentials_store = "auto"
|
|
332
348
|
model = "gpt-5.6-sol"
|
|
333
349
|
model_reasoning_effort = "xhigh"
|
|
334
350
|
model_reasoning_summary = "detailed"
|
|
@@ -382,32 +398,34 @@ permissions. See [Local security model](#local-security-model).
|
|
|
382
398
|
|
|
383
399
|
### Deep-scan engine configuration
|
|
384
400
|
|
|
385
|
-
|
|
386
|
-
engine reads `$CODEX_HOME/codex-security/config.toml`, defaulting to
|
|
401
|
+
Deep scans read `$CODEX_HOME/codex-security/config.toml`, defaulting to
|
|
387
402
|
`~/.codex/codex-security/config.toml`:
|
|
388
403
|
|
|
389
404
|
```toml
|
|
390
405
|
[deep_scan]
|
|
391
|
-
workers =
|
|
406
|
+
workers = 4
|
|
392
407
|
subagents = 3
|
|
393
|
-
stop_after_no_new =
|
|
394
|
-
|
|
408
|
+
stop_after_no_new = 4
|
|
409
|
+
stop_after_consecutive_errors = 3
|
|
410
|
+
max_discovery_runs = 40
|
|
395
411
|
max_time_hours = 96
|
|
396
412
|
```
|
|
397
413
|
|
|
398
|
-
|
|
399
|
-
|
|
400
|
-
|
|
401
|
-
`stop_after_no_new` and `max_discovery_runs`
|
|
402
|
-
`max_time_hours` must be a positive finite number no
|
|
403
|
-
hours are supported. Unknown `[deep_scan]` keys are
|
|
414
|
+
The default is four discovery workers; the legacy `workers = "auto"` setting
|
|
415
|
+
also resolves to four. Set `workers` to a positive integer to choose an explicit
|
|
416
|
+
count. `subagents` must be a nonnegative integer;
|
|
417
|
+
`stop_after_no_new`, `stop_after_consecutive_errors`, and `max_discovery_runs`
|
|
418
|
+
must be positive integers. `max_time_hours` must be a positive finite number no
|
|
419
|
+
greater than 96; fractional hours are supported. Unknown `[deep_scan]` keys are
|
|
420
|
+
rejected.
|
|
404
421
|
|
|
405
422
|
These settings are separate from Codex's
|
|
406
423
|
`features.multi_agent_v2.max_concurrent_threads_per_session` and
|
|
407
424
|
`bulk-scan --workers`. Standalone CLI and SDK scans create an isolated
|
|
408
425
|
`CODEX_HOME`, import the ambient `[deep_scan]` configuration, and apply explicit
|
|
409
|
-
CLI or SDK options on top.
|
|
410
|
-
|
|
426
|
+
CLI or SDK options on top. Set `stop_after_consecutive_errors` in the
|
|
427
|
+
configuration file. Use `--codex` to adjust the Codex session thread limit, not
|
|
428
|
+
to set `[deep_scan]` values.
|
|
411
429
|
|
|
412
430
|
### Environment variables
|
|
413
431
|
|
|
@@ -416,6 +434,8 @@ The CLI and SDK recognize the following user-configurable environment:
|
|
|
416
434
|
| Variable | Effect |
|
|
417
435
|
| --------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------- |
|
|
418
436
|
| `OPENAI_API_KEY`, `CODEX_API_KEY` | Scan authentication; `OPENAI_API_KEY` wins when both are present. |
|
|
437
|
+
| `CODEX_SECURITY_LINEAR_TEAM`, `CODEX_SECURITY_LINEAR_PROJECT` | Default Linear team and project for completed-scan publication. |
|
|
438
|
+
| `CODEX_SECURITY_LINEAR_API_KEY` | Publish directly to Linear with a personal API key; safer than a command-line key. |
|
|
419
439
|
| `CODEX_SECURITY_LOG_LEVEL` | CLI-only; set to `debug` for verbose diagnostics. |
|
|
420
440
|
| `LOG_LEVEL` | CLI-only fallback when `CODEX_SECURITY_LOG_LEVEL` is unset. |
|
|
421
441
|
| `CODEX_SECURITY_STATE_DIR` | Override the private scan-history, workbench, and default artifact directory. |
|
|
@@ -428,6 +448,10 @@ The CLI and SDK recognize the following user-configurable environment:
|
|
|
428
448
|
| `CI` | Disable interactive update notices in automated environments. |
|
|
429
449
|
| `NO_COLOR`, `TERM` | Disable colored scan-history output when `NO_COLOR` is defined or `TERM=dumb`. |
|
|
430
450
|
|
|
451
|
+
On Windows, `CODEX_CLI_PATH` must name a native `.exe` or `.com`. Command
|
|
452
|
+
shims such as `codex.cmd` automatically use the bundled Codex executable
|
|
453
|
+
instead.
|
|
454
|
+
|
|
431
455
|
Interpreter discovery uses `--python` or `pythonPath` first, then `PYTHON`,
|
|
432
456
|
the managed Codex runtime, and finally `python3` or `python` from `PATH`.
|
|
433
457
|
`CODEX_SECURITY_STATE_DIR` takes precedence over `CODEX_HOME`; keep both
|
|
@@ -486,6 +510,7 @@ it returns a sealed partial report with any completed findings and lists
|
|
|
486
510
|
unvalidated candidates as follow-up work. Requests already in progress can
|
|
487
511
|
finish above the limit; preparing the partial report makes no additional model
|
|
488
512
|
requests. Incomplete coverage retains its existing exit code.
|
|
513
|
+
For `bulk-scan`, the limit applies separately to each repository attempt.
|
|
489
514
|
|
|
490
515
|
Run `npx @openai/codex-security scan --help` or `npx @openai/codex-security bulk-scan --help`
|
|
491
516
|
for the complete CLI references.
|
|
@@ -518,28 +543,144 @@ Use `--post-scan-prompt-file PATH` to run a follow-up in the same authenticated
|
|
|
518
543
|
session after each scan, including incomplete or failed scans. Canceled scans
|
|
519
544
|
and scans stopped at their configured cost limit do not start another turn.
|
|
520
545
|
|
|
521
|
-
`--workers`
|
|
522
|
-
|
|
546
|
+
`--workers` sets the number of concurrent repository scans and defaults to
|
|
547
|
+
`4`. `--max-attempts` sets how many times each pending repository can run per
|
|
548
|
+
invocation and defaults to `1`. Results remain under `--output-dir`; rerun the
|
|
549
|
+
same command to resume.
|
|
550
|
+
|
|
551
|
+
### Publish completed scans to Linear
|
|
552
|
+
|
|
553
|
+
Publish every finding from a completed standard, deep, or scoped scan to one
|
|
554
|
+
Linear team:
|
|
555
|
+
|
|
556
|
+
```bash
|
|
557
|
+
npx @openai/codex-security publish scan /path/to/completed-scan \
|
|
558
|
+
--to linear \
|
|
559
|
+
--linear-team TEAM_ID
|
|
560
|
+
```
|
|
561
|
+
|
|
562
|
+
Add `--project PROJECT_ID` to place the issues in a Linear project. Without a
|
|
563
|
+
project, issues are created directly in the selected team.
|
|
564
|
+
|
|
565
|
+
To choose from all completed scans saved in your local scan history, omit the
|
|
566
|
+
scan directory. The selector highlights each repository and shows its finding
|
|
567
|
+
count, relative run time, and abbreviated scan ID:
|
|
568
|
+
|
|
569
|
+
```bash
|
|
570
|
+
npx @openai/codex-security publish scan \
|
|
571
|
+
--to linear \
|
|
572
|
+
--linear-team TEAM_ID
|
|
573
|
+
```
|
|
574
|
+
|
|
575
|
+
Destination flags take precedence over `CODEX_SECURITY_LINEAR_TEAM` and the
|
|
576
|
+
optional `CODEX_SECURITY_LINEAR_PROJECT`. Use `--dry-run` to preview the issue
|
|
577
|
+
titles without creating them, or `--json` to return structured publication
|
|
578
|
+
results.
|
|
579
|
+
Interactive publication shows a full-screen activity view with live Codex
|
|
580
|
+
output and issue-creation progress. Other terminals receive plain progress on
|
|
581
|
+
stderr, so `--json` output remains machine-readable.
|
|
582
|
+
|
|
583
|
+
By default, publishing starts Codex with your existing Codex configuration and
|
|
584
|
+
connected Linear app. Sign in to Codex and connect Linear before publishing in
|
|
585
|
+
this mode. No separate Linear API token is required, and publication does not
|
|
586
|
+
use the isolated Codex home created for security scans.
|
|
587
|
+
|
|
588
|
+
To publish directly through the Linear API without starting Codex, configure a
|
|
589
|
+
Linear personal API key:
|
|
590
|
+
|
|
591
|
+
```bash
|
|
592
|
+
export CODEX_SECURITY_LINEAR_API_KEY=YOUR_LINEAR_PERSONAL_API_KEY
|
|
593
|
+
npx @openai/codex-security publish scan /path/to/completed-scan \
|
|
594
|
+
--to linear \
|
|
595
|
+
--linear-team TEAM_ID
|
|
596
|
+
```
|
|
597
|
+
|
|
598
|
+
Direct API publication leaves issues unassigned by default. Pass
|
|
599
|
+
`--linear-assignee teammate@example.com` or `--linear-assignee USER_ID` to
|
|
600
|
+
assign the issues to a Linear user by email address or user ID.
|
|
601
|
+
`--linear-assignee` requires direct API publication.
|
|
602
|
+
|
|
603
|
+
You can also pass `--linear-api-key KEY`, which takes precedence over
|
|
604
|
+
`CODEX_SECURITY_LINEAR_API_KEY`. Prefer the environment variable to avoid
|
|
605
|
+
exposing your API key in shell history and process listings. API keys are not
|
|
606
|
+
added to successful publication results, scan history, or sealed scan artifacts.
|
|
607
|
+
Error messages are preserved as returned. `--dry-run` never contacts Linear in
|
|
608
|
+
either mode.
|
|
609
|
+
|
|
610
|
+
Each finding creates a separate new issue titled
|
|
611
|
+
`[Codex Security][HIGH] Finding title`. The issue includes the scan ID,
|
|
612
|
+
repository, scanned scope, source locations and code snippets, severity,
|
|
613
|
+
confidence, vulnerability classification, summary, and remediation guidance.
|
|
614
|
+
Verified immutable Git revisions include source links. Findings are published
|
|
615
|
+
concurrently in batches of up to 20. Successful issue identifiers are linked
|
|
616
|
+
to their findings in the local scan-history database, and structured results
|
|
617
|
+
are read back from that database rather than generated by Codex. The completed
|
|
618
|
+
scan must already exist in the local scan history. Running publication again
|
|
619
|
+
creates another set of issues for the same scan; existing issues are not
|
|
620
|
+
matched, updated, or reused.
|
|
621
|
+
|
|
622
|
+
Issue descriptions contain source code and vulnerability details. Select a
|
|
623
|
+
Linear destination authorized to receive that information. Publication receipts
|
|
624
|
+
are stored separately from the sealed scan artifacts.
|
|
625
|
+
|
|
626
|
+
You can also publish a scan from TypeScript:
|
|
627
|
+
|
|
628
|
+
```ts
|
|
629
|
+
import { publishScan } from "@openai/codex-security";
|
|
630
|
+
|
|
631
|
+
const publication = await publishScan("/path/to/completed-scan", {
|
|
632
|
+
destination: "linear",
|
|
633
|
+
teamId: "TEAM_ID",
|
|
634
|
+
onProgress: (progress) => {
|
|
635
|
+
if (progress.type === "issue_completed") {
|
|
636
|
+
console.error(
|
|
637
|
+
`Processed ${progress.completed} of ${progress.total} findings.`,
|
|
638
|
+
);
|
|
639
|
+
}
|
|
640
|
+
},
|
|
641
|
+
});
|
|
642
|
+
|
|
643
|
+
console.log(publication.scanId);
|
|
644
|
+
console.log(publication.created.length);
|
|
645
|
+
```
|
|
646
|
+
|
|
647
|
+
Add `projectId: "PROJECT_ID"` to the options to publish into a specific Linear
|
|
648
|
+
project instead of directly to the team.
|
|
649
|
+
|
|
650
|
+
Pass `linearApiKey` to publish directly through the Linear API. Omit
|
|
651
|
+
`assigneeId` to leave issues unassigned, or supply a Linear user ID or email
|
|
652
|
+
address to select an assignee:
|
|
653
|
+
|
|
654
|
+
```ts
|
|
655
|
+
const directPublication = await publishScan("/path/to/completed-scan", {
|
|
656
|
+
destination: "linear",
|
|
657
|
+
teamId: "TEAM_ID",
|
|
658
|
+
linearApiKey: process.env["CODEX_SECURITY_LINEAR_API_KEY"],
|
|
659
|
+
assigneeId: "teammate@example.com",
|
|
660
|
+
});
|
|
661
|
+
```
|
|
523
662
|
|
|
524
663
|
### Scan history and reruns
|
|
525
664
|
|
|
526
|
-
`
|
|
527
|
-
|
|
528
|
-
|
|
529
|
-
scan
|
|
665
|
+
`scans` or `scans list` lists scans for the current repository. Pass a repository
|
|
666
|
+
path to inspect another checkout, or `--scan-root DIR` to list scans whose
|
|
667
|
+
artifacts are under a particular root. `scans show` opens the latest completed
|
|
668
|
+
scan for the current repository. Pass `SCAN_ID` to inspect another scan. Scan
|
|
669
|
+
details include the configuration, results, coverage, and artifact locations. Add
|
|
530
670
|
`--show-linked-findings` to include finding links from previous scans.
|
|
531
671
|
|
|
532
|
-
`scans logs
|
|
533
|
-
|
|
672
|
+
`scans logs` shows session events from the latest scan, including an active scan.
|
|
673
|
+
Pass `SCAN_ID` to select another scan. Logs can contain source code and credentials.
|
|
534
674
|
|
|
535
675
|
Every scan history command accepts a full scan ID or a unique prefix of at
|
|
536
676
|
least eight characters.
|
|
537
677
|
|
|
538
|
-
Scan history uses
|
|
539
|
-
|
|
540
|
-
`
|
|
541
|
-
are never stored in the scan
|
|
542
|
-
bulk-scan receipts omit messages
|
|
678
|
+
Scan history uses `$CODEX_SECURITY_STATE_DIR/workbench.sqlite3` when
|
|
679
|
+
`CODEX_SECURITY_STATE_DIR` is set. Otherwise, it uses
|
|
680
|
+
`$CODEX_HOME/state/plugins/codex-security/workbench.sqlite3`; `CODEX_HOME`
|
|
681
|
+
defaults to `~/.codex`. Scan credentials are never stored in the scan
|
|
682
|
+
configuration. Recorded failure summaries and bulk-scan receipts omit messages
|
|
683
|
+
that contain recognizable credentials.
|
|
543
684
|
|
|
544
685
|
The scan sandbox permits writes to the selected state directory so SQLite can
|
|
545
686
|
maintain its database and journal files. If the host itself cannot write to the
|
|
@@ -549,22 +690,25 @@ default directory, select a writable directory outside the scanned repository:
|
|
|
549
690
|
export CODEX_SECURITY_STATE_DIR=/path/to/writable/codex-security-state
|
|
550
691
|
```
|
|
551
692
|
|
|
552
|
-
|
|
553
|
-
|
|
554
|
-
|
|
693
|
+
`findings` or `findings list` lists open findings for the current repository.
|
|
694
|
+
Use `findings false-positive OCCURRENCE_ID --reason TEXT` to mark a finding as a
|
|
695
|
+
false positive and explain why. Later scans dismiss a matching finding only when
|
|
696
|
+
the same reason still applies.
|
|
555
697
|
|
|
556
|
-
`scans rerun
|
|
557
|
-
|
|
698
|
+
`scans rerun` repeats the latest completed scan against the current checkout.
|
|
699
|
+
Pass `SCAN_ID` to rerun another scan.
|
|
558
700
|
|
|
559
701
|
`scans match BEFORE_SCAN_ID AFTER_SCAN_ID` links findings with the same root
|
|
560
702
|
cause; `scans match --all` matches all completed scans of the current repository,
|
|
561
703
|
including other worktrees and clones. Saved matches appear in `scans show` and
|
|
562
704
|
are reused unless `--force` is passed. Scans without sealed artifacts are skipped.
|
|
563
705
|
|
|
564
|
-
`scans compare
|
|
565
|
-
|
|
566
|
-
|
|
567
|
-
|
|
706
|
+
`scans compare` compares the two latest completed scans. Pass one scan ID to
|
|
707
|
+
compare it with the latest completed scan, or two IDs to select both scans. It
|
|
708
|
+
matches findings by root cause, reuses saved matches, and reports findings as
|
|
709
|
+
new, persisting, reopened, resolved, or unknown. Missing findings are not
|
|
710
|
+
treated as resolved when the later scan is incomplete or does not cover their
|
|
711
|
+
original scope.
|
|
568
712
|
|
|
569
713
|
The CLI uses [Incur](https://github.com/wevm/incur) for agent-friendly discovery
|
|
570
714
|
and structured output. Inspect the command manifest with `--llms`, inspect a
|
|
@@ -596,7 +740,8 @@ they do not produce structured CLI output. Sign-in commands remain interactive.
|
|
|
596
740
|
CSV exports cannot be written to stdout while JSON output is requested.
|
|
597
741
|
|
|
598
742
|
Use `export` to create CSV, JSON, or SARIF from a completed, sealed scan without
|
|
599
|
-
starting Codex or loading credentials.
|
|
743
|
+
starting Codex or loading credentials. Without a scan directory, it exports the
|
|
744
|
+
latest completed scan for the current repository. JSON preserves the sealed findings
|
|
600
745
|
document. CSV uses the portable findings columns, marks findings as open, and
|
|
601
746
|
does not include local workbench triage state. The exporter validates the seal
|
|
602
747
|
before writing, accepts `--output -` for stdout, and can use
|
|
@@ -647,7 +792,7 @@ from the root of the Codex Security repository:
|
|
|
647
792
|
mkdir -p results state
|
|
648
793
|
chmod 700 results state
|
|
649
794
|
export CODEX_SECURITY_USER="$(id -u):$(id -g)"
|
|
650
|
-
export CODEX_SECURITY_IMAGE=ghcr.io/openai/codex-security:
|
|
795
|
+
export CODEX_SECURITY_IMAGE=ghcr.io/openai/codex-security:latest
|
|
651
796
|
docker compose pull codex-security
|
|
652
797
|
docker compose run --rm codex-security login --device-auth
|
|
653
798
|
docker compose run --rm codex-security
|
|
@@ -683,12 +828,13 @@ repository, Git installation, configured tools, and other scans under the
|
|
|
683
828
|
same account are not separate security principals.
|
|
684
829
|
|
|
685
830
|
Every scan uses the `codex_security_scan` filesystem profile and
|
|
686
|
-
`approvalPolicy: "never"`.
|
|
687
|
-
workspace roots and the selected scan state directory. Scans do not
|
|
688
|
-
interactive approval
|
|
831
|
+
`approvalPolicy: "never"`. Its profile allows reads of the local filesystem and
|
|
832
|
+
writes to workspace roots and the selected scan state directory. Scans do not
|
|
833
|
+
request interactive approval or grant filesystem escalations. Setting
|
|
834
|
+
`approval_policy`, `approvals_reviewer`, `sandbox_mode`, or permissions
|
|
689
835
|
through `--codex` or SDK `codexOverrides` does not replace these controls or
|
|
690
|
-
make
|
|
691
|
-
restrictions still apply.
|
|
836
|
+
make the filesystem profile more restrictive. Independently enforced host and
|
|
837
|
+
network restrictions still apply.
|
|
692
838
|
|
|
693
839
|
Scan and workbench subprocesses can inherit your environment, including
|
|
694
840
|
unrelated API tokens and cloud credentials. Start a scan with only the
|
|
@@ -29,8 +29,10 @@
|
|
|
29
29
|
"AWS_CONTAINER_AUTHORIZATION_TOKEN_FILE",
|
|
30
30
|
"PYTHON",
|
|
31
31
|
"CODEX_SECURITY_KNOWLEDGE_BASE",
|
|
32
|
+
"CODEX_SECURITY_DEEP_SCAN_CONFIG_PATH",
|
|
32
33
|
"CODEX_SECURITY_SCAN_ROOT",
|
|
33
34
|
"CODEX_SECURITY_STATE_DIR",
|
|
35
|
+
"CODEX_SECURITY_SURFACE",
|
|
34
36
|
"HTTP_PROXY",
|
|
35
37
|
"HTTPS_PROXY",
|
|
36
38
|
"ALL_PROXY",
|
|
@@ -21,7 +21,7 @@
|
|
|
21
21
|
},
|
|
22
22
|
"scope": {
|
|
23
23
|
"includePaths": [
|
|
24
|
-
"
|
|
24
|
+
"."
|
|
25
25
|
],
|
|
26
26
|
"excludePaths": []
|
|
27
27
|
},
|
|
@@ -35,7 +35,7 @@
|
|
|
35
35
|
},
|
|
36
36
|
{
|
|
37
37
|
"path": "coverage.json",
|
|
38
|
-
"sha256": "
|
|
38
|
+
"sha256": "d55b9b98d48323b4659dfee6531ec83ec538f2084325412b7188bf85ad68b01b",
|
|
39
39
|
"mediaType": "application/json"
|
|
40
40
|
}
|
|
41
41
|
]
|
|
Binary file
|
|
Binary file
|
|
@@ -65,28 +65,9 @@ capability = "usable_worker_slots_6"
|
|
|
65
65
|
severity = "warn"
|
|
66
66
|
reason = "A six-thread cap provides room for an independent baseline and parallel investigators; it does not require six running workers."
|
|
67
67
|
|
|
68
|
-
[[profiles.security_scan.requirements]]
|
|
69
|
-
capability = "goal_tools"
|
|
70
|
-
severity = "suggest"
|
|
71
|
-
reason = "Goal tools help long scans preserve completion criteria across interruptions and compaction."
|
|
72
|
-
|
|
73
|
-
[[profiles.security_scan.requirements]]
|
|
74
|
-
capability = "goals_enabled"
|
|
75
|
-
severity = "suggest"
|
|
76
|
-
reason = "Enabling goals makes long scans easier to resume and audit."
|
|
77
|
-
|
|
78
68
|
[profiles.deep_security_scan]
|
|
79
69
|
description = "Capabilities for deep repository-wide Codex Security scans."
|
|
80
|
-
|
|
81
|
-
[[profiles.deep_security_scan.requirements]]
|
|
82
|
-
capability = "goal_tools"
|
|
83
|
-
severity = "suggest"
|
|
84
|
-
reason = "Goal tools help long deep scans preserve completion criteria across many rounds."
|
|
85
|
-
|
|
86
|
-
[[profiles.deep_security_scan.requirements]]
|
|
87
|
-
capability = "goals_enabled"
|
|
88
|
-
severity = "suggest"
|
|
89
|
-
reason = "Enabling goals makes long deep scans easier to resume and audit."
|
|
70
|
+
requirements = []
|
|
90
71
|
|
|
91
72
|
[profiles.security_diff_scan.remediation]
|
|
92
73
|
summary = "Recommended Codex config for longer diff scans."
|
|
@@ -95,20 +76,6 @@ summary = "Recommended Codex config for longer diff scans."
|
|
|
95
76
|
path = "features.goals"
|
|
96
77
|
value = true
|
|
97
78
|
|
|
98
|
-
[profiles.security_scan.remediation]
|
|
99
|
-
summary = "Recommended Codex config for repository-wide or scoped-path scans."
|
|
100
|
-
|
|
101
|
-
[[profiles.security_scan.remediation.patches]]
|
|
102
|
-
path = "features.goals"
|
|
103
|
-
value = true
|
|
104
|
-
|
|
105
|
-
[profiles.deep_security_scan.remediation]
|
|
106
|
-
summary = "Recommended Codex setup for deep repository-wide scans."
|
|
107
|
-
|
|
108
|
-
[[profiles.deep_security_scan.remediation.patches]]
|
|
109
|
-
path = "features.goals"
|
|
110
|
-
value = true
|
|
111
|
-
|
|
112
79
|
[[routes]]
|
|
113
80
|
skill = "security-diff-scan"
|
|
114
81
|
profile = "security_diff_scan"
|
|
@@ -1,20 +1,20 @@
|
|
|
1
1
|
# Codex Security Config Preflight
|
|
2
2
|
|
|
3
|
-
Codex Security
|
|
3
|
+
Codex Security Standard and diff scan skills should run the read-only helper before substantive scan work. Deep scans have no parent capability requirements and do not run this helper.
|
|
4
4
|
|
|
5
5
|
Load `desktop-config-preflight.md` only after the host explicitly identifies itself as the Codex desktop app.
|
|
6
6
|
|
|
7
|
-
Resolve `<python_command>` to the configured Python interpreter (
|
|
7
|
+
Resolve `<python_command>` to the configured Python interpreter (`"$PYTHON"` in POSIX shells or `& "$env:PYTHON"` in PowerShell), otherwise use `python` on Windows and `python3` on Unix-like hosts. Before constructing the first helper command, inspect the current tool surface once and use that discovery result for both the runtime checks and `<verified-multi-agent-runtime-arguments>`. Do not omit active runtime facts from the first invocation and wait for an `incomplete` result before supplying them. The command is written on one line so it works in PowerShell, Command Prompt, and POSIX shells:
|
|
8
8
|
|
|
9
9
|
```text
|
|
10
|
-
<python_command> <plugin_dir>/scripts/config_preflight.py --profile <capability-profile> --cwd <scan-working-directory> --runtime-check delegation_available=<true|false>
|
|
10
|
+
<python_command> <plugin_dir>/scripts/config_preflight.py --profile <capability-profile> --cwd <scan-working-directory> --runtime-check delegation_available=<true|false> <verified-multi-agent-runtime-arguments>
|
|
11
11
|
```
|
|
12
12
|
|
|
13
|
-
Determine the runtime-check values from the current tool surface. Delegation tools may be deferred instead of appearing in the initial active tool list. If `tool_search` is available and delegation tools are not already active, search for subagent or multi-agent tools before passing `--runtime-check delegation_available=false`. Pass `false` only after tool discovery fails to expose a usable delegation tool. Consume the discovered tool namespace as runtime evidence too: when the current tool surface exposes `multi_agent_v1`, replace `<verified-multi-agent-runtime-arguments>` with `--multi-agent-runtime-owner native --multi-agent-runtime-version v1 --multi-agent-runtime-provenance tool-surface`. Do not pass a V2 session cap for V1. For other runtimes, use the verified owner, version, capacity when required, and provenance described below. When static config fully describes the active mode and no session-selected runtime overrides it, remove the placeholder. When the runtime exposes a more accurate effective config value than the user's base config file, add `--effective-config <path>=<json-value>`.
|
|
13
|
+
Determine the runtime-check values from the current tool surface. Delegation tools may be deferred instead of appearing in the initial active tool list. If `tool_search` is available and delegation tools are not already active, search for subagent or multi-agent tools before passing `--runtime-check delegation_available=false`. Pass `false` only after tool discovery fails to expose a usable delegation tool. The `security_diff_scan` profile additionally retains its existing `--runtime-check goal_tools_available=<true|false>`; Standard and Deep profiles do not inspect or require goal tools. Consume the discovered tool namespace as runtime evidence too: when the current tool surface exposes `multi_agent_v1`, replace `<verified-multi-agent-runtime-arguments>` with `--multi-agent-runtime-owner native --multi-agent-runtime-version v1 --multi-agent-runtime-provenance tool-surface`. Do not pass a V2 session cap for V1. For other runtimes, use the verified owner, version, capacity when required, and provenance described below. When static config fully describes the active mode and no session-selected runtime overrides it, remove the placeholder. When the runtime exposes a more accurate effective config value than the user's base config file, add `--effective-config <path>=<json-value>`.
|
|
14
14
|
|
|
15
15
|
For standard and diff scans, a passed `delegated_workers` check means the runtime supports delegated review and the explicitly invoked scan authorizes it; a worker-slot result is the configured maximum, not a promise that every worker will start. If the runtime forbids delegation, pass `delegation_available=false`, continue on the documented parent fallback, and do not describe configured slots as running workers or reduced coverage.
|
|
16
16
|
|
|
17
|
-
When `CODEX_SECURITY_CONFIG_PATH` is set, add `--config "$CODEX_SECURITY_CONFIG_PATH"`
|
|
17
|
+
When `CODEX_SECURITY_CONFIG_PATH` is set, add `--config "$CODEX_SECURITY_CONFIG_PATH"` in POSIX shells or `--config "$env:CODEX_SECURITY_CONFIG_PATH"` in PowerShell. The CLI provides this sanitized, shell-readable copy of the active worker configuration because the credential-bearing `CODEX_HOME` is intentionally inaccessible to repository-influenced commands. Do not substitute an ambient Codex home in that case.
|
|
18
18
|
|
|
19
19
|
Otherwise, the helper discovers Codex config paths itself from `--cwd`, which defaults to the current working directory. It reads `/etc/codex/config.toml`, then `$CODEX_HOME/config.toml`, resolves `project_root_markers`, checks the matching `[projects."<absolute-project-root>"].trust_level`, and loads trusted project `.codex/config.toml` layers from the project root down to `--cwd`. It does not load project layers unless the user config marks that project root as `trusted`.
|
|
20
20
|
|
|
@@ -22,8 +22,6 @@ When the current Codex CLI session selected `-p/--profile <name>`, pass `--codex
|
|
|
22
22
|
|
|
23
23
|
For targeted tests or unusual runtimes, repeated `--config <path>` arguments override automatic discovery. Pass those manual layers from lower to higher precedence.
|
|
24
24
|
|
|
25
|
-
Repeat `--available-plugin-skill <skill-name>` only for skills from the capability's plugin when the selected profile checks skill dependencies. For the `deep_security_scan` profile, expose only the plugin-local names of available `codex-security` skills, such as `security-scan`; do not pass unrelated session skills. Use the current session's Available skills surface, not files found on disk. The helper reports unavailable skills as a runtime problem and a missing runtime plugin skill list as `incomplete`.
|
|
26
|
-
|
|
27
25
|
In Codex CLI, run the helper directly in the parent even when delegation is available. This keeps the exact command, exit code, and JSON result in the CLI event stream and avoids attributing an unobservable child result to the active runtime. In other hosts with delegation, run preflight in one dedicated worker before substantive scan work. Dispatch means a successful worker-spawn tool call that returns a concrete worker or thread id. Do not claim that a worker is running, or call a generic wait with no receiver, unless that spawn succeeded. Wait for the specific returned id and accept a result only from that worker. If spawning fails or returns no id, run the helper directly in the parent and report the spawn failure; never invent or reconstruct a helper result. The worker should return only a compact summary: the executed command and exit code, overall status, unmet or unknown capabilities, the returned `user_config_path`, and applicable remediation. Include the source path for any conflicting setting. Do not return the helper's raw JSON unless the parent needs it to resolve an ambiguity. This keeps preflight inspection out of the primary scan context.
|
|
28
26
|
|
|
29
27
|
The parent should pass only the runtime facts the worker cannot establish itself, such as a selected config profile or effective runtime-only config values. If delegation is unavailable after tool discovery, run the helper directly in the parent so the preflight can report the degraded or blocked path.
|
|
@@ -34,7 +32,7 @@ Multi-agent config mode is auto-detected when static config fully describes it.
|
|
|
34
32
|
--multi-agent-runtime-owner native --multi-agent-runtime-version v2 --multi-agent-session-cap <count> --multi-agent-runtime-provenance <app-server|thread-context|tool-surface>
|
|
35
33
|
```
|
|
36
34
|
|
|
37
|
-
The V2 session cap includes the root thread. For profiles that evaluate current-session worker capacity, the helper subtracts that root thread when evaluating usable worker slots. For native V2 selected by static config, the documented Codex default session cap is four when no explicit cap is configured. Do not apply that static default to model- or session-selected V2 when a profile needs the active capacity: pass the observed runtime cap, or
|
|
35
|
+
The V2 session cap includes the root thread. For profiles that evaluate current-session worker capacity, the helper subtracts that root thread when evaluating usable worker slots. For native V2 selected by static config, the documented Codex default session cap is four when no explicit cap is configured. Do not apply that static default to model- or session-selected V2 when a profile needs the active capacity: pass the observed runtime cap, or a blocking capacity requirement remains `incomplete`.
|
|
38
36
|
|
|
39
37
|
When the active session is actually managed by `codex_bridge`, provide explicit verified ownership. A backend config value alone is not ownership evidence:
|
|
40
38
|
|
|
@@ -42,9 +40,9 @@ When the active session is actually managed by `codex_bridge`, provide explicit
|
|
|
42
40
|
--multi-agent-runtime-owner codex-bridge --multi-agent-runtime-version v2 --multi-agent-runtime-provenance verified-bridge --effective-config multiagent_config.max_concurrency=<count>
|
|
43
41
|
```
|
|
44
42
|
|
|
45
|
-
|
|
43
|
+
For a profile that evaluates parent-runtime settings, passing `multiagent_config.max_concurrency` without `--multi-agent-runtime-owner codex-bridge` and `verified-bridge` provenance is an error. Explicit runtime claims still require their existing provenance and ownership checks. An unrelated backend config value does not block a profile that does not use parent-runtime settings.
|
|
46
44
|
|
|
47
|
-
Static native V2 accepts both `[features] multi_agent_v2 = true` and `[features.multi_agent_v2] enabled = true`.
|
|
45
|
+
Static native V2 accepts both `[features] multi_agent_v2 = true` and `[features.multi_agent_v2] enabled = true`. When the profile evaluates parent-runtime settings or explicit runtime facts are supplied, native V2 cannot be combined with `agents.max_threads`. `agents.max_depth` applies to V1 only and is not required for V2. A runtime version and cap without verified ownership cannot satisfy a blocking requirement. When runtime version, ownership, or capacity remains unknown, the helper returns `incomplete` only when a blocking requirement needs that fact and omits unsafe concurrency patches.
|
|
48
46
|
|
|
49
47
|
The helper reads the routed capability profile from `../preflight/capability-profiles.toml`, discovers the applicable Codex config paths from `--cwd`, applies documented defaults where the registry provides them, and prints one JSON result.
|
|
50
48
|
|
|
@@ -66,7 +64,7 @@ Deep Security Scan uses MCP-owned SDK sessions rather than the parent thread's w
|
|
|
66
64
|
|
|
67
65
|
Do not warn merely because a user's value differs from the profile's suggested patch. Warn or block only when the evaluated capability requirement is unmet.
|
|
68
66
|
|
|
69
|
-
If a runtime capability is `unknown`, establish it from the current tool surface and rerun the helper with an explicit `--runtime-check`.
|
|
67
|
+
If a blocking runtime capability is `unknown`, establish it from the current tool surface and rerun the helper with an explicit `--runtime-check`. An unknown `warn` or `suggest` capability does not block a `ready` scan; continue on the documented degraded path without claiming that capability is available.
|
|
70
68
|
|
|
71
69
|
## Durable scan handoff
|
|
72
70
|
|
|
@@ -104,11 +102,11 @@ request_user_input(
|
|
|
104
102
|
)
|
|
105
103
|
```
|
|
106
104
|
|
|
107
|
-
Do not set `autoResolutionMs`; in an interactive session, an explicit answer is required before persistent configuration changes or scan continuation. If native `request_user_input` is unavailable or errors, call `request_codex_security_user_input` with the same `questions` payload. This MCP fallback is interactive and must remain prohibited in non-interactive sessions. If it returns `accepted`, follow its answer. If it is unavailable or errors, ask the same choices in chat. If it returns `declined` or `cancelled`, do not infer a choice; preserve the running scan, stop, and state that an explicit answer is still required. In every interactive waiting case, stop for the user's answer before creating or adopting a scan goal. Do not call `fail_codex_security_scan` while waiting for that answer. Apply only the approved remediation after `Apply and retry`, preserve the running scan and stop after `Leave paused`, and call `
|
|
105
|
+
Do not set `autoResolutionMs`; in an interactive session, an explicit answer is required before persistent configuration changes or scan continuation. If native `request_user_input` is unavailable or errors, call `request_codex_security_user_input` with the same `questions` payload. This MCP fallback is interactive and must remain prohibited in non-interactive sessions. If it returns `accepted`, follow its answer. If it is unavailable or errors, ask the same choices in chat. If it returns `declined` or `cancelled`, do not infer a choice; preserve the running scan, stop, and state that an explicit answer is still required. In every interactive waiting case, stop for the user's answer before creating or adopting a scan goal. Do not call `fail_codex_security_scan` while waiting for that answer. Apply only the approved remediation after `Apply and retry`, preserve the running scan and stop after `Leave paused`, and call `cancel_codex_security_scan` after `Cancel scan`.
|
|
108
106
|
|
|
109
107
|
In a non-interactive Codex session, do not leave the run waiting for an answer it cannot receive. After showing the exact blocker and config delta, automatically apply only the helper's concrete Codex config patches with ordinary `value` or `remove` operations to the active writable user config, preserving unrelated settings. Never automatically apply `host_setting` remediation or invent a patch. Rerun the same preflight once with the same verified runtime facts and any newly observable effective config. Continue only after that rerun returns `ready`; do not create or adopt scan goals or start substantive scan work earlier. If the new config needs a fresh session before the active runtime can use it, the rerun remains blocked or incomplete, remediation is unavailable, or the helper errors, do not loop, call `fail_codex_security_scan`, or cancel automatically. Preserve an app-generated durable scan and hand it off for a later retry; in CLI or another host without a durable scan, report the exact remaining blocker and end without claiming that a scan is paused.
|
|
110
108
|
|
|
111
|
-
For any non-ready result, do not fail automatically. If an interactive chat fallback declines required remediation without choosing whether to cancel or leave the scan running, ask that follow-up before taking either action. If remediation is unavailable, the helper cannot run, the helper returns an error envelope, or a rerun remains blocked or incomplete, preserve a durable running scan and retry or hand off while recovery may still be possible. Call `fail_codex_security_scan` with the exact reasons only after the documented recovery path is exhausted and the blocker is confirmed unrecoverable
|
|
109
|
+
For any non-ready result, do not fail automatically. If an interactive chat fallback declines required remediation without choosing whether to cancel or leave the scan running, ask that follow-up before taking either action. If remediation is unavailable, the helper cannot run, the helper returns an error envelope, or a rerun remains blocked or incomplete, preserve a durable running scan and retry or hand off while recovery may still be possible. Call `fail_codex_security_scan` with the exact reasons only after the documented recovery path is exhausted and the blocker is confirmed unrecoverable. When the user explicitly cancels, call `cancel_codex_security_scan`.
|
|
112
110
|
|
|
113
111
|
Present applicable remediation in the Codex thread. Ask before editing persistent user configuration in interactive sessions; use the narrow automatic-remediation path above in non-interactive sessions.
|
|
114
112
|
|