@mokuyoaxis/agent-guard 0.2.3-rc2 → 0.2.4
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 +127 -83
- package/README.zh-CN.md +106 -74
- package/adapters/INTEGRATION.md +4 -4
- package/adapters/claude/README.md +3 -3
- package/adapters/claude/harness/README.md +1 -1
- package/adapters/codex/harness/README.md +2 -2
- package/adapters/dsh/README.md +24 -15
- package/adapters/dsh/harness/README.md +75 -19
- package/adapters/dsh/harness/bootstrap.patch.yml +5 -0
- package/adapters/dsh/harness/bootstrap_init.mjs +48 -0
- package/adapters/dsh/harness/guard_lab.py +194 -32
- package/adapters/dsh/harness/native_session.py +41 -20
- package/adapters/dsh/harness/profiles.py +74 -22
- package/adapters/dsh/lib/index.js +1 -1
- package/adapters/kimi-code/README.md +15 -14
- package/adapters/kimi-code/harness/README.md +3 -3
- package/adapters/kimi-code/harness/guard_lab.py +1 -1
- package/core/__init__.py +1 -1
- package/core/classifier.py +41 -16
- package/core/lab.py +24 -1
- package/core/policy.py +11 -4
- package/core/recovery.py +256 -23
- package/core/redaction.py +157 -55
- package/core/trash_index.py +193 -0
- package/docs/README.md +104 -0
- package/docs/{architecture.md → design/architecture.md} +31 -6
- package/docs/{compatibility.md → design/compatibility.md} +54 -4
- package/docs/{threat-model.md → design/threat-model.md} +4 -4
- package/docs/{harness-capabilities.md → guides/harness-capabilities.md} +9 -9
- package/docs/guides/trash-index.md +106 -0
- package/docs/{development-note-unguarded-deletion.md → history/development-note-unguarded-deletion.md} +8 -9
- package/docs/{friction.md → history/friction.md} +107 -4
- package/docs/{secret-guard-analysis.md → history/secret-guard-analysis.md} +23 -22
- package/docs/{secret-guard-architecture.md → history/secret-guard-architecture.md} +6 -4
- package/docs/{secret-guard-design.md → history/secret-guard-design.md} +19 -15
- package/docs/lab/cases/injection-case-fake-ai-api.md +346 -0
- package/docs/{guard-lab.md → lab/guard-lab.md} +18 -11
- package/docs/lab/tasks/guard-lab-read-trial-task.md +7 -0
- package/docs/{release-notes-0.2.0-rc1.md → releases/release-notes-0.2.0-rc1.md} +5 -5
- package/docs/{release-notes-0.2.0.md → releases/release-notes-0.2.0.md} +7 -7
- package/docs/{release-notes-0.2.1.md → releases/release-notes-0.2.1.md} +6 -6
- package/docs/{release-notes-0.2.2.md → releases/release-notes-0.2.2.md} +9 -10
- package/docs/{release-notes-0.2.3-rc1.md → releases/release-notes-0.2.3-rc1.md} +4 -2
- package/docs/{release-notes-0.2.3-rc2.md → releases/release-notes-0.2.3-rc2.md} +9 -9
- package/docs/releases/release-notes-0.2.3.md +84 -0
- package/docs/releases/release-notes-0.2.4.md +89 -0
- package/docs/{test-report-claude-code-harness.md → reports/test-report-claude-code-harness.md} +5 -5
- package/docs/{test-report-codex-gpt-5.6-sol.md → reports/test-report-codex-gpt-5.6-sol.md} +10 -11
- package/docs/reports/test-report-dsh-0.2.4-ptc.md +79 -0
- package/docs/{test-report-dsh-guard-lab.md → reports/test-report-dsh-guard-lab.md} +1 -1
- package/docs/{test-report-dsh-native-session.md → reports/test-report-dsh-native-session.md} +1 -1
- package/docs/{test-report-dsh-paired-lab.md → reports/test-report-dsh-paired-lab.md} +1 -1
- package/docs/{test-report-dsh-real-followup.md → reports/test-report-dsh-real-followup.md} +1 -1
- package/docs/{test-report-dsh-retry-evidence.md → reports/test-report-dsh-retry-evidence.md} +1 -1
- package/docs/{test-report-dsh-v0.1.1.md → reports/test-report-dsh-v0.1.1.md} +4 -4
- package/docs/{test-report-kimi-code-block.md → reports/test-report-kimi-code-block.md} +22 -23
- package/docs/{test-report-kimi-guard-lab.md → reports/test-report-kimi-guard-lab.md} +3 -3
- package/docs/{test-report-release-readiness-0.2.3.md → reports/test-report-release-readiness-0.2.3.md} +79 -1
- package/docs/reports/test-report-workbuddy-windows-core.md +53 -0
- package/docs/{test-report-zcode-glm-flash.md → reports/test-report-zcode-glm-flash.md} +11 -11
- package/package.json +1 -1
- package/skills/delete-guard/SKILL.md +40 -3
- package/skills/delete-guard/references/policy.md +18 -5
- package/skills/delete-guard/scripts/check.py +19 -0
- package/skills/delete-guard/scripts/restore.py +18 -6
- package/skills/delete-guard/scripts/status.py +52 -0
- package/skills/exfil-guard/SKILL.md +37 -7
- package/skills/exfil-guard/references/channels.md +1 -1
- package/skills/exfil-guard/references/rules.md +84 -16
- package/skills/exfil-guard/scripts/_payload.py +99 -0
- package/skills/exfil-guard/scripts/check_span.py +14 -81
- package/skills/exfil-guard/scripts/sanitize.py +113 -34
- package/docs/release-notes-0.2.3.md +0 -45
- /package/docs/{host-drift.md → guides/host-drift.md} +0 -0
- /package/docs/{publishing-from-ephemeral-environments.md → guides/publishing-from-ephemeral-environments.md} +0 -0
- /package/docs/{guard-lab-clean-task.md → lab/tasks/guard-lab-clean-task.md} +0 -0
- /package/docs/{guard-lab-trial-task.md → lab/tasks/guard-lab-trial-task.md} +0 -0
- /package/docs/{test-report-codex-gpt-6-astra-high.md → reports/test-report-codex-gpt-6-astra-high.md} +0 -0
- /package/docs/{test-report-dsh-0.1.5-rc.1.md → reports/test-report-dsh-0.1.5-rc.1.md} +0 -0
- /package/docs/{test-report-dsh-0.2-upgrade.md → reports/test-report-dsh-0.2-upgrade.md} +0 -0
- /package/docs/{test-report-dsh-read-redaction.md → reports/test-report-dsh-read-redaction.md} +0 -0
package/README.md
CHANGED
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
[](https://www.npmjs.com/package/@mokuyoaxis/agent-guard)
|
|
5
5
|
[](LICENSE)
|
|
6
6
|
[](https://www.python.org/)
|
|
7
|
-
[](docs/releases/release-notes-0.2.4.md)
|
|
8
8
|
|
|
9
9
|
**Make destructive agent actions reversible by default.** · [简体中文](README.zh-CN.md)
|
|
10
10
|
|
|
@@ -38,33 +38,34 @@ integration bridges rather than the product boundary.
|
|
|
38
38
|
```text
|
|
39
39
|
rm -rf build/ → RELOCATE # an in-scope tree moves to quarantine
|
|
40
40
|
rm -rf . → BLOCK # the workspace root is protected
|
|
41
|
-
git reset --hard → SNAPSHOT #
|
|
41
|
+
git reset --hard → SNAPSHOT # after collision preflight, snapshot tracked changes
|
|
42
42
|
git push --force → BLOCK # remote history is not automated
|
|
43
43
|
```
|
|
44
44
|
|
|
45
45
|
These are illustrative verdicts for supported inputs, not commands to run or
|
|
46
46
|
proof that every harness intercepts them. Ignored, regenerable targets may be
|
|
47
|
-
`ALLOW`;
|
|
48
|
-
|
|
49
|
-
|
|
47
|
+
`ALLOW`; hard reset is blocked if its target tree would overwrite untracked
|
|
48
|
+
or ignored content, or if its preflight/snapshot cannot be completed. When
|
|
49
|
+
recovery or safe rewriting is possible, the agent can keep working. Otherwise,
|
|
50
|
+
the guard asks the human or blocks the operation.
|
|
50
51
|
|
|
51
52
|
## Quick start with your coding agent
|
|
52
53
|
|
|
53
|
-
Use the scoped npm package
|
|
54
|
-
|
|
55
|
-
package.
|
|
54
|
+
Use the scoped npm package or a stable Git checkout. The unscoped
|
|
55
|
+
`agent-guard` package is unrelated to this project.
|
|
56
56
|
|
|
57
57
|
Pinned npm installation into a stable, user-owned prefix:
|
|
58
58
|
|
|
59
59
|
```sh
|
|
60
|
-
npm install --prefix /absolute/path/to/agent-guard-install @mokuyoaxis/agent-guard@0.2.
|
|
60
|
+
npm install --prefix /absolute/path/to/agent-guard-install @mokuyoaxis/agent-guard@0.2.4
|
|
61
61
|
```
|
|
62
62
|
|
|
63
|
-
|
|
64
|
-
|
|
65
|
-
|
|
66
|
-
|
|
67
|
-
|
|
63
|
+
**0.2.4** adds hard-reset collision checks,
|
|
64
|
+
restore path validation, current-version preservation on forced restore, and
|
|
65
|
+
a read-only trash location query. See the [release notes](docs/releases/release-notes-0.2.4.md)
|
|
66
|
+
for behavior changes and evidence limits. The npm badge and
|
|
67
|
+
[GitHub Releases](https://github.com/mokuyoaxis/agent-guard/releases) show
|
|
68
|
+
which artifacts are available.
|
|
68
69
|
|
|
69
70
|
The package root is then
|
|
70
71
|
`/absolute/path/to/agent-guard-install/node_modules/@mokuyoaxis/agent-guard`.
|
|
@@ -81,8 +82,10 @@ the host's hook support. Then give your coding agent the following setup prompt
|
|
|
81
82
|
|
|
82
83
|
```text
|
|
83
84
|
Set up agent-guard for this workspace. Use either an existing Git checkout or
|
|
84
|
-
the exact scoped npm package @mokuyoaxis/agent-guard@0.2.
|
|
85
|
-
unscoped package named agent-guard.
|
|
85
|
+
the exact scoped npm package @mokuyoaxis/agent-guard@0.2.4;
|
|
86
|
+
never install the unscoped package named agent-guard. If 0.2.4 is unavailable,
|
|
87
|
+
report that and use the existing checkout or ask me to choose a published
|
|
88
|
+
version. Before installing, ask me to choose and
|
|
86
89
|
approve a stable user-owned prefix. Treat the checkout or installed package
|
|
87
90
|
root as /absolute/path/to/agent-guard below.
|
|
88
91
|
First identify the current harness and its actual hook/skill capabilities;
|
|
@@ -103,7 +106,7 @@ intercepted, and any unverified paths.
|
|
|
103
106
|
```
|
|
104
107
|
|
|
105
108
|
For manual setup and evidence limits, see the
|
|
106
|
-
[adapter matrix](docs/harness-capabilities.md) and the adapter README for your
|
|
109
|
+
[adapter matrix](docs/guides/harness-capabilities.md) and the adapter README for your
|
|
107
110
|
host.
|
|
108
111
|
|
|
109
112
|
## Design principles
|
|
@@ -213,7 +216,7 @@ DSH also offers a [default-off text-read redaction prototype](adapters/dsh/READM
|
|
|
213
216
|
for complete native reads in a pinned composition. It reuses Core and
|
|
214
217
|
regenerates both rendered text and presentation metadata; a zero-model native
|
|
215
218
|
probe covers the next request and durable JSONL log. A separate
|
|
216
|
-
[official Flash direct-read trial](docs/test-report-dsh-real-followup.md)
|
|
219
|
+
[official Flash direct-read trial](docs/reports/test-report-dsh-real-followup.md)
|
|
217
220
|
observed supported synthetic-secret redaction while useful config stayed readable.
|
|
218
221
|
|
|
219
222
|
It is a prevention and redaction guard, not a compensation engine: after an
|
|
@@ -236,19 +239,27 @@ cannot rewrite what it did not write):
|
|
|
236
239
|
|
|
237
240
|
### What is detected
|
|
238
241
|
|
|
239
|
-
**T1 vendor credential patterns** (`secret
|
|
240
|
-
|
|
242
|
+
**T1 vendor credential patterns** (`secret/*`). These rules use known formats;
|
|
243
|
+
documented placeholders and negative examples constrain false positives.
|
|
244
|
+
Rule ids: `secret/openai-key`, `secret/github-token`,
|
|
241
245
|
`secret/aws-access-key-id`, `secret/gitlab-token`, `secret/slack-token`,
|
|
242
|
-
`secret/stripe-key` (live keys only — `sk_test_` is exempt),
|
|
243
|
-
(structural: the header must
|
|
246
|
+
`secret/stripe-key` (live keys only — `sk_test_` is exempt),
|
|
247
|
+
`secret/pypi-token`, `secret/jwt` (structural: the header must decode to JSON
|
|
248
|
+
with a nonempty ASCII string `alg`), and
|
|
244
249
|
`secret/private-key-block` (whole `-----BEGIN ... PRIVATE KEY-----` block,
|
|
245
250
|
redacted in one piece). See
|
|
246
251
|
[skills/exfil-guard/references/rules.md](skills/exfil-guard/references/rules.md)
|
|
247
|
-
for the
|
|
252
|
+
for the rule table and remaining ambiguities.
|
|
253
|
+
|
|
254
|
+
`secret/connection-password` also detects nonempty passwords in URI userinfo.
|
|
255
|
+
It redacts only the password, preserving the scheme, account and host for
|
|
256
|
+
diagnostics. Percent-encoded passwords and JSON-escaped scheme slashes are
|
|
257
|
+
supported; this does not hide network topology or scan every DSN format.
|
|
248
258
|
|
|
249
259
|
**Value-free secret references** (`secret/source-reference`). The guard
|
|
250
|
-
classifies an environment variable's *name* (
|
|
251
|
-
|
|
260
|
+
classifies complete components in an environment variable's *name* (such as
|
|
261
|
+
`KEY`, `TOKEN`, `SECRET`, `PASSWORD`, `PASSWD`, `CRED`, or `AUTH`) and a
|
|
262
|
+
secret-store *file name*
|
|
252
263
|
(`.env`, `*.pem`, `id_rsa*`, `.netrc`, `kubeconfig`, ...), and detects
|
|
253
264
|
whole-environment expansions (`printenv`, `env | ...`, `cat
|
|
254
265
|
/proc/self/environ`). This scanner **does not resolve the variable value**;
|
|
@@ -304,6 +315,28 @@ Exit code contract: `0` = ALLOW/SANITIZED · `2` = BLOCK · `3` = ASK ·
|
|
|
304
315
|
and placeholders only — **never the matched bytes**), and `--path` to enable
|
|
305
316
|
the repo-local exemption file for the file being written.
|
|
306
317
|
|
|
318
|
+
`sanitize.py` enforces the same exit codes: ASK/BLOCK and errors emit no
|
|
319
|
+
payload on stdout. It validates an external `--plan` against the current scan
|
|
320
|
+
and rescans the rewritten text before emitting. Both CLIs use the same default
|
|
321
|
+
workspace and host-side mode; stdin is bounded to the scan cap (4 MiB by default)
|
|
322
|
+
during reading, as is an external plan file. A checker plan produced with an
|
|
323
|
+
explicit mode or path exemption must still satisfy the sanitizer's current
|
|
324
|
+
policy; the plan itself does not authorize emission.
|
|
325
|
+
|
|
326
|
+
Credential detection covers classic and stateless `ghs_APPID_JWT` GitHub
|
|
327
|
+
installation tokens, including long signatures and credentials next to CJK
|
|
328
|
+
prose. Placeholder exemptions require whole shapes; incidental example words
|
|
329
|
+
inside a token do not exempt it. Secret variable references are classified by
|
|
330
|
+
complete name components, preserving ordinary identifiers such as `MONKEY`
|
|
331
|
+
and metadata such as `TOKEN_COUNT`. See the [rule reference](skills/exfil-guard/references/rules.md)
|
|
332
|
+
for supported forms and limitations.
|
|
333
|
+
|
|
334
|
+
PyPI publishing tokens are also detected with their documented prefix and
|
|
335
|
+
minimum body shape, with complete redaction of long tokens. AWS group/user/
|
|
336
|
+
role/policy IDs are kept distinct from access-key IDs; JWT headers require
|
|
337
|
+
the declared nonempty ASCII string `alg`. Public-key variable names and the
|
|
338
|
+
broad legacy `sk-` shape retain their documented conservative boundaries.
|
|
339
|
+
|
|
307
340
|
### Read a config without printing its values
|
|
308
341
|
|
|
309
342
|
Introduced in the `0.2.0` source; this CLI is **not** in the earlier
|
|
@@ -353,14 +386,14 @@ is a false security claim:
|
|
|
353
386
|
call with no proxy, the model's own tool calls, content produced *inside* a
|
|
354
387
|
program, and the human clipboard get **no verdict at all** — no coverage is
|
|
355
388
|
claimed there. See `references/channels.md` and
|
|
356
|
-
[docs/secret-guard-analysis.md](docs/secret-guard-analysis.md) §2.4 for
|
|
389
|
+
[docs/history/secret-guard-analysis.md](docs/history/secret-guard-analysis.md) §2.4 for
|
|
357
390
|
the reachability table this claim is traceable to.
|
|
358
391
|
- **Not a file scanner.** It is not a gitleaks replacement; it scans what the
|
|
359
392
|
guard can see *on the way out*.
|
|
360
393
|
- **No history rewriting.** Detecting a secret already in Git history is a
|
|
361
394
|
report at most. Rewriting history is a human action with its own risks.
|
|
362
|
-
- **No T3 entropy detector in this release.**
|
|
363
|
-
|
|
395
|
+
- **No T3 entropy detector in this release.** Random-looking text alone is
|
|
396
|
+
insufficient evidence of a credential; ordinary identifiers stay readable.
|
|
364
397
|
|
|
365
398
|
## Manual, harness-neutral usage
|
|
366
399
|
|
|
@@ -373,6 +406,7 @@ python3 skills/delete-guard/scripts/safe_delete.py build/ --reason "stale"
|
|
|
373
406
|
|
|
374
407
|
# inspect and undo:
|
|
375
408
|
python3 skills/delete-guard/scripts/status.py
|
|
409
|
+
python3 skills/delete-guard/scripts/status.py --trash-index --root <projects> --json
|
|
376
410
|
python3 skills/delete-guard/scripts/restore.py list
|
|
377
411
|
python3 skills/delete-guard/scripts/restore.py <txid>
|
|
378
412
|
|
|
@@ -380,6 +414,11 @@ python3 skills/delete-guard/scripts/restore.py <txid>
|
|
|
380
414
|
python3 skills/delete-guard/scripts/gc.py
|
|
381
415
|
```
|
|
382
416
|
|
|
417
|
+
The local [trash location query](docs/guides/trash-index.md) provides a shared
|
|
418
|
+
read-only JSON interface for agents and future UI callers. It reports scoped
|
|
419
|
+
location candidates and layout hints; it neither scans recovery contents nor
|
|
420
|
+
grants cleanup permission. It is included in 0.2.4.
|
|
421
|
+
|
|
383
422
|
A harness adapter can invoke the guard before a supported shell command and
|
|
384
423
|
map its exit status to the host's own tool decision:
|
|
385
424
|
|
|
@@ -394,7 +433,7 @@ exit 1 → guard error; fail closed
|
|
|
394
433
|
## What gets protected
|
|
395
434
|
|
|
396
435
|
These examples assume the command reaches the guard and its targets meet the
|
|
397
|
-
stated conditions; see the [capability matrix](docs/harness-capabilities.md)
|
|
436
|
+
stated conditions; see the [capability matrix](docs/guides/harness-capabilities.md)
|
|
398
437
|
for what each host has actually demonstrated.
|
|
399
438
|
|
|
400
439
|
```text
|
|
@@ -405,7 +444,8 @@ rm *.log → BLOCK (opaque glob; safe_delete expands it)
|
|
|
405
444
|
cd X && rm -rf build → ASK_ONCE (COMPOUND_CWD_DELETE)
|
|
406
445
|
touch f && rm f → ASK_ONCE (COMPOUND_CREATE_DELETE)
|
|
407
446
|
git clean -fd → RELOCATE (enumerate via -n, relocate, proceed)
|
|
408
|
-
git reset --hard → SNAPSHOT (
|
|
447
|
+
git reset --hard → SNAPSHOT (collision preflight + tracked snapshot)
|
|
448
|
+
reset with collisions → BLOCK (preserve untracked/ignored paths first)
|
|
409
449
|
git push --force → BLOCK (remote history is never automated)
|
|
410
450
|
node_modules/ (ignored) → ALLOW (provably regenerable)
|
|
411
451
|
quarantine full → BLOCK (never fall back to permanent delete)
|
|
@@ -413,12 +453,18 @@ quarantine full → BLOCK (never fall back to permanent delete)
|
|
|
413
453
|
|
|
414
454
|
## Integration and validation matrix
|
|
415
455
|
|
|
416
|
-
[](docs/test-report-codex-gpt-6-astra-high.md)
|
|
418
|
-
[](docs/test-report-dsh-0.1.5-rc.1.md)
|
|
419
|
-
[](docs/test-report-zcode-glm-flash.md)
|
|
420
|
-
[](docs/test-report-claude-code-harness.md)
|
|
421
|
-
[](.github/workflows/ci.yml)
|
|
457
|
+
[](docs/reports/test-report-codex-gpt-6-astra-high.md)
|
|
458
|
+
[](docs/reports/test-report-dsh-0.1.5-rc.1.md)
|
|
459
|
+
[](docs/reports/test-report-zcode-glm-flash.md)
|
|
460
|
+
[](docs/reports/test-report-claude-code-harness.md)
|
|
461
|
+
[](docs/reports/test-report-kimi-code-block.md)
|
|
462
|
+
[](docs/reports/test-report-workbuddy-windows-core.md)
|
|
463
|
+
[](docs/releases/release-notes-0.2.3-rc1.md#focused-windows-ci)
|
|
464
|
+
[](docs/reports/test-report-release-readiness-0.2.3.md)
|
|
465
|
+
|
|
466
|
+
These badges link to scoped evidence; they do not certify every tool or model.
|
|
467
|
+
The DSH text-read feature is optional and off by default.
|
|
422
468
|
|
|
423
469
|
"The Core works", "a Skill-guided agent used it", and "the harness
|
|
424
470
|
intercepts every matching tool call" are separate claims. This table keeps
|
|
@@ -426,13 +472,14 @@ those evidence levels explicit:
|
|
|
426
472
|
|
|
427
473
|
| Harness / tested version | Integration path | Evidence and limit |
|
|
428
474
|
|---|---|---|
|
|
429
|
-
| **Claude Code 2.1.270 / 2.1.273** | [Native `PreToolUse` for Bash](adapters/claude/README.md) | [Real CLI + scripted model](docs/test-report-claude-code-harness.md): sampled allow/ask/deny and Python-startup failure; other tools unverified. |
|
|
430
|
-
| **DSH 0.1.5-rc.1** | [Native pre-execute adapter](adapters/dsh/README.md) | [Real-host packaged-plugin probe](docs/test-report-dsh-0.1.5-rc.1.md): execution-level `BLOCK` and loaded-adapter Core failure. A [real-model Lab baseline](docs/test-report-dsh-guard-lab.md) stayed quiet with guard off, so no L2 mitigation claim exists; model-proposed destructive `bash` enforcement remains unverified. The separate opt-in read path is listed below. |
|
|
431
|
-
| **DSH CLI rc.1 / tools and FS rc.2 / Node 22** | [Experimental text-read redaction](adapters/dsh/README.md#experimental-text-read-redaction), default off | [Zero-model native probe](docs/test-report-dsh-read-redaction.md): next request and durable JSONL. [Official Flash direct-read off/on](docs/test-report-dsh-real-followup.md): supported synthetic secrets redacted in tool content/meta/session, useful config preserved; no injection L2 claim. |
|
|
432
|
-
| **DSH 0.2.0-rc.2 / Node 22** | [Default deletion and optional text-read adapter](adapters/dsh/README.md) | [Fresh contract review](docs/test-report-release-readiness-0.2.3.md): native deletion blocking, read redaction on reviewed local/sandbox FS, next synthetic request and durable JSONL. Native v4 Lab support remains bounded; no new real-model L2 result. |
|
|
433
|
-
| **Codex CLI 0.154.0 (tested session)** | [Skill + production CLI](docs/test-report-codex-gpt-6-astra-high.md) | Older-source cooperative acceptance; no native hook claim. |
|
|
434
|
-
| **
|
|
435
|
-
| **
|
|
475
|
+
| **Claude Code 2.1.270 / 2.1.273** | [Native `PreToolUse` for Bash](adapters/claude/README.md) | [Real CLI + scripted model](docs/reports/test-report-claude-code-harness.md): sampled allow/ask/deny and Python-startup failure; other tools unverified. |
|
|
476
|
+
| **DSH 0.1.5-rc.1** | [Native pre-execute adapter](adapters/dsh/README.md) | [Real-host packaged-plugin probe](docs/reports/test-report-dsh-0.1.5-rc.1.md): execution-level `BLOCK` and loaded-adapter Core failure. A [real-model Lab baseline](docs/reports/test-report-dsh-guard-lab.md) stayed quiet with guard off, so no L2 mitigation claim exists; model-proposed destructive `bash` enforcement remains unverified. The separate opt-in read path is listed below. |
|
|
477
|
+
| **DSH CLI rc.1 / tools and FS rc.2 / Node 22** | [Experimental text-read redaction](adapters/dsh/README.md#experimental-text-read-redaction), default off | [Zero-model native probe](docs/reports/test-report-dsh-read-redaction.md): next request and durable JSONL. [Official Flash direct-read off/on](docs/reports/test-report-dsh-real-followup.md): supported synthetic secrets redacted in tool content/meta/session, useful config preserved; no injection L2 claim. |
|
|
478
|
+
| **DSH 0.2.0-rc.2 / Node 22** | [Default deletion and optional text-read adapter](adapters/dsh/README.md) | [Fresh contract review](docs/reports/test-report-release-readiness-0.2.3.md): native deletion blocking, read redaction on reviewed local/sandbox FS, next synthetic request and durable JSONL. Native v4 Lab support remains bounded; no new real-model L2 result. |
|
|
479
|
+
| **Codex CLI 0.154.0 (tested session)** | [Skill + production CLI](docs/reports/test-report-codex-gpt-6-astra-high.md) | Older-source cooperative acceptance; no native hook claim. |
|
|
480
|
+
| **WorkBuddy (version not recorded; Windows 11)** | [Core / CLI](docs/reports/test-report-workbuddy-windows-core.md) | Community feedback on 0.2.2 found two Core defects now covered by regressions and focused Windows CI; no WorkBuddy adapter or native-hook validation. |
|
|
481
|
+
| **ZCode (version unrecorded; win32)** | [Historical Skill/CLI + hook trial](docs/reports/test-report-zcode-glm-flash.md) | Older hook observation includes a persistent-permission bypass; current version unverified. |
|
|
482
|
+
| **Kimi Code 0.42.0 / 2.1.1** | [Native `PreToolUse` for Bash](adapters/kimi-code/README.md) | [Bounded tests](docs/reports/test-report-kimi-code-block.md): authenticated 2.1.1 root-Bash PASS on an OAuth official model and a second configured model route; older 0.42.0 root/child BLOCK, ASK denial and Python-failure refusal. Hook absence/timeout remains fail-open. |
|
|
436
483
|
| **Other / unlisted hosts** | [Self-adaptation guide](adapters/INTEGRATION.md) | No native claim without a blocking pre-tool event and independent non-execution check. |
|
|
437
484
|
|
|
438
485
|
For agent-led setup: identify the actual host version and tool names, follow
|
|
@@ -456,7 +503,7 @@ configuration/runtime fingerprints. It reports `CURRENT`, `STALE`,
|
|
|
456
503
|
`DRIFTED`, `BROKEN`, or `UNVERIFIED`; even `CURRENT` is static preflight
|
|
457
504
|
evidence, not interception proof. Optional create-new baselines contain only
|
|
458
505
|
the parsed version and SHA-256 fingerprints. See the
|
|
459
|
-
[host drift guide](docs/host-drift.md) for the status and baseline contract.
|
|
506
|
+
[host drift guide](docs/guides/host-drift.md) for the status and baseline contract.
|
|
460
507
|
An explicit `--live-sentinel` can then spend one configured model call in a
|
|
461
508
|
private blank fixture. It reports `PASS`, `FAIL`, or `INCONCLUSIVE` with
|
|
462
509
|
`NONE`/`NOTICE`, `CRITICAL`, or `WARNING`; marker absence alone never passes.
|
|
@@ -466,7 +513,7 @@ The optional Kimi doctor needs Python 3.11+ for TOML parsing; the Core and
|
|
|
466
513
|
hook adapter continue to support Python 3.9+.
|
|
467
514
|
See the [Kimi](adapters/kimi-code/README.md) and
|
|
468
515
|
[Claude](adapters/claude/README.md) adapter guides.
|
|
469
|
-
See [harness capabilities and evidence levels](docs/harness-capabilities.md)
|
|
516
|
+
See [harness capabilities and evidence levels](docs/guides/harness-capabilities.md)
|
|
470
517
|
for the per-host scope and execution-level acceptance criteria.
|
|
471
518
|
|
|
472
519
|
## Repository layout
|
|
@@ -486,7 +533,7 @@ agent-guard/
|
|
|
486
533
|
├── adapters/dsh/ # DeepSeek Harness integration bridge
|
|
487
534
|
├── adapters/codex/harness/# CLI acceptance driver; not a native hook
|
|
488
535
|
├── tests/ # unittest suites incl. cross-harness conformance
|
|
489
|
-
└── docs/ #
|
|
536
|
+
└── docs/ # guides · design · Lab · reports · releases · history
|
|
490
537
|
```
|
|
491
538
|
|
|
492
539
|
Skills guide agent behavior; constraints live in Core. Future
|
|
@@ -495,25 +542,19 @@ compensation engine without restructuring.
|
|
|
495
542
|
|
|
496
543
|
## Documentation
|
|
497
544
|
|
|
545
|
+
The [documentation index](docs/README.md) lists every document by purpose.
|
|
546
|
+
Historical reports retain their tested versions and evidence limits.
|
|
547
|
+
|
|
498
548
|
| Read | For |
|
|
499
549
|
|---|---|
|
|
500
550
|
| [CONTRIBUTING.md](CONTRIBUTING.md) | how to propose an Issue and submit a focused Pull Request |
|
|
501
|
-
| [
|
|
502
|
-
| [
|
|
503
|
-
| [
|
|
504
|
-
| [
|
|
505
|
-
| [
|
|
506
|
-
| [
|
|
507
|
-
| [docs/release-notes-0.2.1.md](docs/release-notes-0.2.1.md) | 0.2.1 adapter/doctor changes and bounded evidence |
|
|
508
|
-
| [docs/release-notes-0.2.0.md](docs/release-notes-0.2.0.md) | 0.2.0 changes, evidence levels, and known limits |
|
|
551
|
+
| [Guides](docs/README.md#guides) | current harness capabilities, host drift and maintainer guidance |
|
|
552
|
+
| [Design and contracts](docs/README.md#design) | architecture, threat model and compatibility |
|
|
553
|
+
| [Lab](docs/README.md#lab) | experiment guide, task templates and candidate attack references |
|
|
554
|
+
| [Test reports](docs/README.md#reports) | versioned Core, CLI, hook and Lab evidence |
|
|
555
|
+
| [Release notes](docs/README.md#releases) | stable and prerelease scopes |
|
|
556
|
+
| [Historical design and findings](docs/README.md#history) | early proposals, friction log and incident exploration |
|
|
509
557
|
| [adapters/INTEGRATION.md](adapters/INTEGRATION.md) | self-adaptation checklist for an unlisted host |
|
|
510
|
-
| [docs/threat-model.md](docs/threat-model.md) | honest limits: what this is and is not |
|
|
511
|
-
| [docs/friction.md](docs/friction.md) | what real agents and host processes taught us (F1–F20) |
|
|
512
|
-
| [docs/development-note-unguarded-deletion.md](docs/development-note-unguarded-deletion.md) | de-identified incident exploration and the recovery-aware direction |
|
|
513
|
-
| [docs/test-report-codex-gpt-5.6-sol.md](docs/test-report-codex-gpt-5.6-sol.md) | v0.1.1 Codex evaluation (medium + high) |
|
|
514
|
-
| [docs/test-report-dsh-0.1.5-rc.1.md](docs/test-report-dsh-0.1.5-rc.1.md) | current DSH packaged-plugin and execution-level `bash` acceptance |
|
|
515
|
-
| [docs/test-report-dsh-guard-lab.md](docs/test-report-dsh-guard-lab.md) | bounded DSH real-model Lab baseline; no L2 claim |
|
|
516
|
-
| [docs/test-report-dsh-v0.1.1.md](docs/test-report-dsh-v0.1.1.md) | v0.1.1 DSH live test (DeepSeek V4 Pro high, minimal mode) |
|
|
517
558
|
| [skills/recovery-audit/SKILL.md](skills/recovery-audit/SKILL.md) | evidence hierarchy, deterministic replay, recovery and landing gates |
|
|
518
559
|
| [skills/delete-guard/references/policy.md](skills/delete-guard/references/policy.md) | full rule table and decision codes |
|
|
519
560
|
| [skills/exfil-guard/references/rules.md](skills/exfil-guard/references/rules.md) | exfil rule table, reason codes, exemption format, audit shape |
|
|
@@ -521,37 +562,40 @@ compensation engine without restructuring.
|
|
|
521
562
|
|
|
522
563
|
## Status & roadmap
|
|
523
564
|
|
|
524
|
-
|
|
525
|
-
|
|
526
|
-
|
|
527
|
-
|
|
528
|
-
|
|
529
|
-
|
|
530
|
-
|
|
531
|
-
|
|
532
|
-
|
|
533
|
-
[0.2.
|
|
534
|
-
[0.2.
|
|
535
|
-
[
|
|
536
|
-
|
|
537
|
-
|
|
538
|
-
|
|
539
|
-
|
|
540
|
-
|
|
565
|
+
**v0.2.4** adds focused recovery maintenance and the trash query
|
|
566
|
+
to 0.2.3. It refuses hard-reset collisions with untracked/ignored content,
|
|
567
|
+
checks restore sources and destinations, and preserves an occupied destination
|
|
568
|
+
before a forced restore. The query supplies a shared CLI/agent/future UI
|
|
569
|
+
contract. Existing text redaction, safe config inspection, offline Lab,
|
|
570
|
+
Claude/Kimi bridges, doctor, host-drift checks and live sentinel remain available.
|
|
571
|
+
The DSH bridge supports the reviewed `0.1.5-rc.1` and `0.2.0-rc.2` contracts;
|
|
572
|
+
its optional text-read protection remains off by default.
|
|
573
|
+
|
|
574
|
+
The [0.2.4 notes](docs/releases/release-notes-0.2.4.md) describe this release's scope.
|
|
575
|
+
The [0.2.3](docs/releases/release-notes-0.2.3.md),
|
|
576
|
+
[rc2](docs/releases/release-notes-0.2.3-rc2.md),
|
|
577
|
+
[rc1](docs/releases/release-notes-0.2.3-rc1.md), and
|
|
578
|
+
[0.2.2](docs/releases/release-notes-0.2.2.md) notes retain their historical scope.
|
|
579
|
+
Check [GitHub Releases](https://github.com/mokuyoaxis/agent-guard/releases)
|
|
580
|
+
and npm for published artifacts.
|
|
581
|
+
|
|
582
|
+
The Core and Decision Protocol are shared across harnesses. DSH, Claude and
|
|
583
|
+
Kimi adapters, together with Codex/WorkBuddy/ZCode acceptance records, are documented in
|
|
584
|
+
one compatibility matrix.
|
|
541
585
|
The Kimi result includes sampled hook-compensation and execution-level BLOCK
|
|
542
586
|
paths, not proof that its host enforces every BLOCK or that arbitrary agent
|
|
543
587
|
actions are protected. A tested direct-Python hook startup failure was
|
|
544
588
|
fail-open. The optional shell bridge blocked a sampled Python startup failure
|
|
545
589
|
in a real Kimi host session, but only when the bridge itself ran; config
|
|
546
590
|
validation alone cannot prove that the hook is live.
|
|
547
|
-
The
|
|
591
|
+
The release adds a focused real-Windows Core gate for Issue #7, but native
|
|
548
592
|
cmd/PowerShell execution through every harness and general concurrent-subagent
|
|
549
593
|
safety remain explicit gaps. Later Guard branches (`git-guard`, `database-guard`,
|
|
550
594
|
`cloud-guard`) reuse the same protocol and compensation engine.
|
|
551
595
|
|
|
552
|
-
##
|
|
596
|
+
## guard-lab
|
|
553
597
|
|
|
554
|
-
The
|
|
598
|
+
The opt-in, offline honeytoken Lab uses disposable
|
|
555
599
|
projects and synthetic, non-secret markers. Its `clean`, `mock-positive`,
|
|
556
600
|
`mock-injection`, and `snapshot-positive` controls call no model and make no
|
|
557
601
|
external request. A bounded loopback observer records the fake Lab stub, bait
|
|
@@ -560,10 +604,10 @@ canary in selected output without retaining the raw value.
|
|
|
560
604
|
|
|
561
605
|
The user keeps the true controller and evidence outside the fixture shown to
|
|
562
606
|
the tested agent. Broken controls or changed evidence produce `INCONCLUSIVE`,
|
|
563
|
-
never an optimistic pass.
|
|
607
|
+
never an optimistic pass. The Lab cannot observe ordinary file
|
|
564
608
|
reads, prove remote transfer, universally block LLM calls, or resist a same-UID
|
|
565
609
|
adversary. Start with the zero-token controls and read the
|
|
566
|
-
[guard-lab guide](docs/guard-lab.md) before involving a real harness.
|
|
610
|
+
[guard-lab guide](docs/lab/guard-lab.md) before involving a real harness.
|
|
567
611
|
The built-in cases report `CALIBRATION_ONLY`. A separate manual
|
|
568
612
|
`injection-probe` treats bait contact as `EXPOSURE_OBSERVED`, and `compare`
|
|
569
613
|
accepts a mitigation result only after an effective unguarded baseline and a
|