@mokuyoaxis/agent-guard 0.2.3-rc2 → 0.2.4-hotfix.1
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 +132 -84
- package/README.zh-CN.md +109 -75
- 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 +66 -17
- package/core/lab.py +24 -1
- package/core/policy.py +28 -13
- 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} +80 -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} +129 -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-hotfix.1.md +75 -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 +29 -9
- 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-hotfix.1.md)
|
|
8
8
|
|
|
9
9
|
**Make destructive agent actions reversible by default.** · [简体中文](README.zh-CN.md)
|
|
10
10
|
|
|
@@ -38,33 +38,38 @@ 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
|
+
After publication, install the exact hotfix 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-hotfix.1
|
|
61
61
|
```
|
|
62
62
|
|
|
63
|
-
|
|
64
|
-
|
|
65
|
-
|
|
66
|
-
|
|
67
|
-
|
|
63
|
+
**0.2.4-hotfix.1** is an opt-in maintenance hotfix based on 0.2.4, adding
|
|
64
|
+
quarantine root/control-path protection. It retains the baseline's hard-reset,
|
|
65
|
+
restore and read-only trash-query behavior. It uses the
|
|
66
|
+
separate npm `hotfix` channel; `latest`, `rc` and the cumulative 0.2.5 RC line
|
|
67
|
+
keep their existing roles. SemVer ranks this suffix below 0.2.4, so users
|
|
68
|
+
must explicitly select the hotfix version or channel. See the
|
|
69
|
+
[hotfix notes](docs/releases/release-notes-0.2.4-hotfix.1.md) for scope and
|
|
70
|
+
validation. The npm badge and
|
|
71
|
+
[GitHub Releases](https://github.com/mokuyoaxis/agent-guard/releases) show
|
|
72
|
+
which artifacts are available.
|
|
68
73
|
|
|
69
74
|
The package root is then
|
|
70
75
|
`/absolute/path/to/agent-guard-install/node_modules/@mokuyoaxis/agent-guard`.
|
|
@@ -81,8 +86,10 @@ the host's hook support. Then give your coding agent the following setup prompt
|
|
|
81
86
|
|
|
82
87
|
```text
|
|
83
88
|
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.
|
|
89
|
+
the exact scoped npm package @mokuyoaxis/agent-guard@0.2.4-hotfix.1;
|
|
90
|
+
never install the unscoped package named agent-guard. If 0.2.4-hotfix.1 is unavailable,
|
|
91
|
+
report that and use the existing checkout or ask me to choose a published
|
|
92
|
+
version. Before installing, ask me to choose and
|
|
86
93
|
approve a stable user-owned prefix. Treat the checkout or installed package
|
|
87
94
|
root as /absolute/path/to/agent-guard below.
|
|
88
95
|
First identify the current harness and its actual hook/skill capabilities;
|
|
@@ -103,7 +110,7 @@ intercepted, and any unverified paths.
|
|
|
103
110
|
```
|
|
104
111
|
|
|
105
112
|
For manual setup and evidence limits, see the
|
|
106
|
-
[adapter matrix](docs/harness-capabilities.md) and the adapter README for your
|
|
113
|
+
[adapter matrix](docs/guides/harness-capabilities.md) and the adapter README for your
|
|
107
114
|
host.
|
|
108
115
|
|
|
109
116
|
## Design principles
|
|
@@ -213,7 +220,7 @@ DSH also offers a [default-off text-read redaction prototype](adapters/dsh/READM
|
|
|
213
220
|
for complete native reads in a pinned composition. It reuses Core and
|
|
214
221
|
regenerates both rendered text and presentation metadata; a zero-model native
|
|
215
222
|
probe covers the next request and durable JSONL log. A separate
|
|
216
|
-
[official Flash direct-read trial](docs/test-report-dsh-real-followup.md)
|
|
223
|
+
[official Flash direct-read trial](docs/reports/test-report-dsh-real-followup.md)
|
|
217
224
|
observed supported synthetic-secret redaction while useful config stayed readable.
|
|
218
225
|
|
|
219
226
|
It is a prevention and redaction guard, not a compensation engine: after an
|
|
@@ -236,19 +243,27 @@ cannot rewrite what it did not write):
|
|
|
236
243
|
|
|
237
244
|
### What is detected
|
|
238
245
|
|
|
239
|
-
**T1 vendor credential patterns** (`secret
|
|
240
|
-
|
|
246
|
+
**T1 vendor credential patterns** (`secret/*`). These rules use known formats;
|
|
247
|
+
documented placeholders and negative examples constrain false positives.
|
|
248
|
+
Rule ids: `secret/openai-key`, `secret/github-token`,
|
|
241
249
|
`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
|
|
250
|
+
`secret/stripe-key` (live keys only — `sk_test_` is exempt),
|
|
251
|
+
`secret/pypi-token`, `secret/jwt` (structural: the header must decode to JSON
|
|
252
|
+
with a nonempty ASCII string `alg`), and
|
|
244
253
|
`secret/private-key-block` (whole `-----BEGIN ... PRIVATE KEY-----` block,
|
|
245
254
|
redacted in one piece). See
|
|
246
255
|
[skills/exfil-guard/references/rules.md](skills/exfil-guard/references/rules.md)
|
|
247
|
-
for the
|
|
256
|
+
for the rule table and remaining ambiguities.
|
|
257
|
+
|
|
258
|
+
`secret/connection-password` also detects nonempty passwords in URI userinfo.
|
|
259
|
+
It redacts only the password, preserving the scheme, account and host for
|
|
260
|
+
diagnostics. Percent-encoded passwords and JSON-escaped scheme slashes are
|
|
261
|
+
supported; this does not hide network topology or scan every DSN format.
|
|
248
262
|
|
|
249
263
|
**Value-free secret references** (`secret/source-reference`). The guard
|
|
250
|
-
classifies an environment variable's *name* (
|
|
251
|
-
|
|
264
|
+
classifies complete components in an environment variable's *name* (such as
|
|
265
|
+
`KEY`, `TOKEN`, `SECRET`, `PASSWORD`, `PASSWD`, `CRED`, or `AUTH`) and a
|
|
266
|
+
secret-store *file name*
|
|
252
267
|
(`.env`, `*.pem`, `id_rsa*`, `.netrc`, `kubeconfig`, ...), and detects
|
|
253
268
|
whole-environment expansions (`printenv`, `env | ...`, `cat
|
|
254
269
|
/proc/self/environ`). This scanner **does not resolve the variable value**;
|
|
@@ -304,6 +319,28 @@ Exit code contract: `0` = ALLOW/SANITIZED · `2` = BLOCK · `3` = ASK ·
|
|
|
304
319
|
and placeholders only — **never the matched bytes**), and `--path` to enable
|
|
305
320
|
the repo-local exemption file for the file being written.
|
|
306
321
|
|
|
322
|
+
`sanitize.py` enforces the same exit codes: ASK/BLOCK and errors emit no
|
|
323
|
+
payload on stdout. It validates an external `--plan` against the current scan
|
|
324
|
+
and rescans the rewritten text before emitting. Both CLIs use the same default
|
|
325
|
+
workspace and host-side mode; stdin is bounded to the scan cap (4 MiB by default)
|
|
326
|
+
during reading, as is an external plan file. A checker plan produced with an
|
|
327
|
+
explicit mode or path exemption must still satisfy the sanitizer's current
|
|
328
|
+
policy; the plan itself does not authorize emission.
|
|
329
|
+
|
|
330
|
+
Credential detection covers classic and stateless `ghs_APPID_JWT` GitHub
|
|
331
|
+
installation tokens, including long signatures and credentials next to CJK
|
|
332
|
+
prose. Placeholder exemptions require whole shapes; incidental example words
|
|
333
|
+
inside a token do not exempt it. Secret variable references are classified by
|
|
334
|
+
complete name components, preserving ordinary identifiers such as `MONKEY`
|
|
335
|
+
and metadata such as `TOKEN_COUNT`. See the [rule reference](skills/exfil-guard/references/rules.md)
|
|
336
|
+
for supported forms and limitations.
|
|
337
|
+
|
|
338
|
+
PyPI publishing tokens are also detected with their documented prefix and
|
|
339
|
+
minimum body shape, with complete redaction of long tokens. AWS group/user/
|
|
340
|
+
role/policy IDs are kept distinct from access-key IDs; JWT headers require
|
|
341
|
+
the declared nonempty ASCII string `alg`. Public-key variable names and the
|
|
342
|
+
broad legacy `sk-` shape retain their documented conservative boundaries.
|
|
343
|
+
|
|
307
344
|
### Read a config without printing its values
|
|
308
345
|
|
|
309
346
|
Introduced in the `0.2.0` source; this CLI is **not** in the earlier
|
|
@@ -353,14 +390,14 @@ is a false security claim:
|
|
|
353
390
|
call with no proxy, the model's own tool calls, content produced *inside* a
|
|
354
391
|
program, and the human clipboard get **no verdict at all** — no coverage is
|
|
355
392
|
claimed there. See `references/channels.md` and
|
|
356
|
-
[docs/secret-guard-analysis.md](docs/secret-guard-analysis.md) §2.4 for
|
|
393
|
+
[docs/history/secret-guard-analysis.md](docs/history/secret-guard-analysis.md) §2.4 for
|
|
357
394
|
the reachability table this claim is traceable to.
|
|
358
395
|
- **Not a file scanner.** It is not a gitleaks replacement; it scans what the
|
|
359
396
|
guard can see *on the way out*.
|
|
360
397
|
- **No history rewriting.** Detecting a secret already in Git history is a
|
|
361
398
|
report at most. Rewriting history is a human action with its own risks.
|
|
362
|
-
- **No T3 entropy detector in this release.**
|
|
363
|
-
|
|
399
|
+
- **No T3 entropy detector in this release.** Random-looking text alone is
|
|
400
|
+
insufficient evidence of a credential; ordinary identifiers stay readable.
|
|
364
401
|
|
|
365
402
|
## Manual, harness-neutral usage
|
|
366
403
|
|
|
@@ -373,6 +410,7 @@ python3 skills/delete-guard/scripts/safe_delete.py build/ --reason "stale"
|
|
|
373
410
|
|
|
374
411
|
# inspect and undo:
|
|
375
412
|
python3 skills/delete-guard/scripts/status.py
|
|
413
|
+
python3 skills/delete-guard/scripts/status.py --trash-index --root <projects> --json
|
|
376
414
|
python3 skills/delete-guard/scripts/restore.py list
|
|
377
415
|
python3 skills/delete-guard/scripts/restore.py <txid>
|
|
378
416
|
|
|
@@ -380,6 +418,11 @@ python3 skills/delete-guard/scripts/restore.py <txid>
|
|
|
380
418
|
python3 skills/delete-guard/scripts/gc.py
|
|
381
419
|
```
|
|
382
420
|
|
|
421
|
+
The local [trash location query](docs/guides/trash-index.md) provides a shared
|
|
422
|
+
read-only JSON interface for agents and future UI callers. It reports scoped
|
|
423
|
+
location candidates and layout hints; it neither scans recovery contents nor
|
|
424
|
+
grants cleanup permission. It is included in 0.2.4.
|
|
425
|
+
|
|
383
426
|
A harness adapter can invoke the guard before a supported shell command and
|
|
384
427
|
map its exit status to the host's own tool decision:
|
|
385
428
|
|
|
@@ -394,7 +437,7 @@ exit 1 → guard error; fail closed
|
|
|
394
437
|
## What gets protected
|
|
395
438
|
|
|
396
439
|
These examples assume the command reaches the guard and its targets meet the
|
|
397
|
-
stated conditions; see the [capability matrix](docs/harness-capabilities.md)
|
|
440
|
+
stated conditions; see the [capability matrix](docs/guides/harness-capabilities.md)
|
|
398
441
|
for what each host has actually demonstrated.
|
|
399
442
|
|
|
400
443
|
```text
|
|
@@ -405,7 +448,8 @@ rm *.log → BLOCK (opaque glob; safe_delete expands it)
|
|
|
405
448
|
cd X && rm -rf build → ASK_ONCE (COMPOUND_CWD_DELETE)
|
|
406
449
|
touch f && rm f → ASK_ONCE (COMPOUND_CREATE_DELETE)
|
|
407
450
|
git clean -fd → RELOCATE (enumerate via -n, relocate, proceed)
|
|
408
|
-
git reset --hard → SNAPSHOT (
|
|
451
|
+
git reset --hard → SNAPSHOT (collision preflight + tracked snapshot)
|
|
452
|
+
reset with collisions → BLOCK (preserve untracked/ignored paths first)
|
|
409
453
|
git push --force → BLOCK (remote history is never automated)
|
|
410
454
|
node_modules/ (ignored) → ALLOW (provably regenerable)
|
|
411
455
|
quarantine full → BLOCK (never fall back to permanent delete)
|
|
@@ -413,12 +457,18 @@ quarantine full → BLOCK (never fall back to permanent delete)
|
|
|
413
457
|
|
|
414
458
|
## Integration and validation matrix
|
|
415
459
|
|
|
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)
|
|
461
|
+
[](docs/reports/test-report-codex-gpt-6-astra-high.md)
|
|
462
|
+
[](docs/reports/test-report-dsh-0.1.5-rc.1.md)
|
|
463
|
+
[](docs/reports/test-report-zcode-glm-flash.md)
|
|
464
|
+
[](docs/reports/test-report-claude-code-harness.md)
|
|
465
|
+
[](docs/reports/test-report-kimi-code-block.md)
|
|
466
|
+
[](docs/reports/test-report-workbuddy-windows-core.md)
|
|
467
|
+
[](docs/releases/release-notes-0.2.3-rc1.md#focused-windows-ci)
|
|
468
|
+
[](docs/reports/test-report-release-readiness-0.2.3.md)
|
|
469
|
+
|
|
470
|
+
These badges link to scoped evidence; they do not certify every tool or model.
|
|
471
|
+
The DSH text-read feature is optional and off by default.
|
|
422
472
|
|
|
423
473
|
"The Core works", "a Skill-guided agent used it", and "the harness
|
|
424
474
|
intercepts every matching tool call" are separate claims. This table keeps
|
|
@@ -426,13 +476,14 @@ those evidence levels explicit:
|
|
|
426
476
|
|
|
427
477
|
| Harness / tested version | Integration path | Evidence and limit |
|
|
428
478
|
|---|---|---|
|
|
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
|
-
| **
|
|
479
|
+
| **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. |
|
|
480
|
+
| **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. |
|
|
481
|
+
| **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. |
|
|
482
|
+
| **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. |
|
|
483
|
+
| **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. |
|
|
484
|
+
| **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. |
|
|
485
|
+
| **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. |
|
|
486
|
+
| **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
487
|
| **Other / unlisted hosts** | [Self-adaptation guide](adapters/INTEGRATION.md) | No native claim without a blocking pre-tool event and independent non-execution check. |
|
|
437
488
|
|
|
438
489
|
For agent-led setup: identify the actual host version and tool names, follow
|
|
@@ -456,7 +507,7 @@ configuration/runtime fingerprints. It reports `CURRENT`, `STALE`,
|
|
|
456
507
|
`DRIFTED`, `BROKEN`, or `UNVERIFIED`; even `CURRENT` is static preflight
|
|
457
508
|
evidence, not interception proof. Optional create-new baselines contain only
|
|
458
509
|
the parsed version and SHA-256 fingerprints. See the
|
|
459
|
-
[host drift guide](docs/host-drift.md) for the status and baseline contract.
|
|
510
|
+
[host drift guide](docs/guides/host-drift.md) for the status and baseline contract.
|
|
460
511
|
An explicit `--live-sentinel` can then spend one configured model call in a
|
|
461
512
|
private blank fixture. It reports `PASS`, `FAIL`, or `INCONCLUSIVE` with
|
|
462
513
|
`NONE`/`NOTICE`, `CRITICAL`, or `WARNING`; marker absence alone never passes.
|
|
@@ -466,7 +517,7 @@ The optional Kimi doctor needs Python 3.11+ for TOML parsing; the Core and
|
|
|
466
517
|
hook adapter continue to support Python 3.9+.
|
|
467
518
|
See the [Kimi](adapters/kimi-code/README.md) and
|
|
468
519
|
[Claude](adapters/claude/README.md) adapter guides.
|
|
469
|
-
See [harness capabilities and evidence levels](docs/harness-capabilities.md)
|
|
520
|
+
See [harness capabilities and evidence levels](docs/guides/harness-capabilities.md)
|
|
470
521
|
for the per-host scope and execution-level acceptance criteria.
|
|
471
522
|
|
|
472
523
|
## Repository layout
|
|
@@ -486,7 +537,7 @@ agent-guard/
|
|
|
486
537
|
├── adapters/dsh/ # DeepSeek Harness integration bridge
|
|
487
538
|
├── adapters/codex/harness/# CLI acceptance driver; not a native hook
|
|
488
539
|
├── tests/ # unittest suites incl. cross-harness conformance
|
|
489
|
-
└── docs/ #
|
|
540
|
+
└── docs/ # guides · design · Lab · reports · releases · history
|
|
490
541
|
```
|
|
491
542
|
|
|
492
543
|
Skills guide agent behavior; constraints live in Core. Future
|
|
@@ -495,25 +546,19 @@ compensation engine without restructuring.
|
|
|
495
546
|
|
|
496
547
|
## Documentation
|
|
497
548
|
|
|
549
|
+
The [documentation index](docs/README.md) lists every document by purpose.
|
|
550
|
+
Historical reports retain their tested versions and evidence limits.
|
|
551
|
+
|
|
498
552
|
| Read | For |
|
|
499
553
|
|---|---|
|
|
500
554
|
| [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 |
|
|
555
|
+
| [Guides](docs/README.md#guides) | current harness capabilities, host drift and maintainer guidance |
|
|
556
|
+
| [Design and contracts](docs/README.md#design) | architecture, threat model and compatibility |
|
|
557
|
+
| [Lab](docs/README.md#lab) | experiment guide, task templates and candidate attack references |
|
|
558
|
+
| [Test reports](docs/README.md#reports) | versioned Core, CLI, hook and Lab evidence |
|
|
559
|
+
| [Release notes](docs/README.md#releases) | stable and prerelease scopes |
|
|
560
|
+
| [Historical design and findings](docs/README.md#history) | early proposals, friction log and incident exploration |
|
|
509
561
|
| [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
562
|
| [skills/recovery-audit/SKILL.md](skills/recovery-audit/SKILL.md) | evidence hierarchy, deterministic replay, recovery and landing gates |
|
|
518
563
|
| [skills/delete-guard/references/policy.md](skills/delete-guard/references/policy.md) | full rule table and decision codes |
|
|
519
564
|
| [skills/exfil-guard/references/rules.md](skills/exfil-guard/references/rules.md) | exfil rule table, reason codes, exemption format, audit shape |
|
|
@@ -521,37 +566,40 @@ compensation engine without restructuring.
|
|
|
521
566
|
|
|
522
567
|
## Status & roadmap
|
|
523
568
|
|
|
524
|
-
|
|
525
|
-
|
|
526
|
-
|
|
527
|
-
|
|
528
|
-
|
|
529
|
-
|
|
530
|
-
|
|
531
|
-
|
|
532
|
-
|
|
533
|
-
[0.2.
|
|
534
|
-
[0.2.
|
|
535
|
-
[
|
|
536
|
-
|
|
537
|
-
|
|
538
|
-
|
|
539
|
-
|
|
540
|
-
|
|
569
|
+
**v0.2.4** adds focused recovery maintenance and the trash query
|
|
570
|
+
to 0.2.3. It refuses hard-reset collisions with untracked/ignored content,
|
|
571
|
+
checks restore sources and destinations, and preserves an occupied destination
|
|
572
|
+
before a forced restore. The query supplies a shared CLI/agent/future UI
|
|
573
|
+
contract. Existing text redaction, safe config inspection, offline Lab,
|
|
574
|
+
Claude/Kimi bridges, doctor, host-drift checks and live sentinel remain available.
|
|
575
|
+
The DSH bridge supports the reviewed `0.1.5-rc.1` and `0.2.0-rc.2` contracts;
|
|
576
|
+
its optional text-read protection remains off by default.
|
|
577
|
+
|
|
578
|
+
The [0.2.4 notes](docs/releases/release-notes-0.2.4.md) describe this release's scope.
|
|
579
|
+
The [0.2.3](docs/releases/release-notes-0.2.3.md),
|
|
580
|
+
[rc2](docs/releases/release-notes-0.2.3-rc2.md),
|
|
581
|
+
[rc1](docs/releases/release-notes-0.2.3-rc1.md), and
|
|
582
|
+
[0.2.2](docs/releases/release-notes-0.2.2.md) notes retain their historical scope.
|
|
583
|
+
Check [GitHub Releases](https://github.com/mokuyoaxis/agent-guard/releases)
|
|
584
|
+
and npm for published artifacts.
|
|
585
|
+
|
|
586
|
+
The Core and Decision Protocol are shared across harnesses. DSH, Claude and
|
|
587
|
+
Kimi adapters, together with Codex/WorkBuddy/ZCode acceptance records, are documented in
|
|
588
|
+
one compatibility matrix.
|
|
541
589
|
The Kimi result includes sampled hook-compensation and execution-level BLOCK
|
|
542
590
|
paths, not proof that its host enforces every BLOCK or that arbitrary agent
|
|
543
591
|
actions are protected. A tested direct-Python hook startup failure was
|
|
544
592
|
fail-open. The optional shell bridge blocked a sampled Python startup failure
|
|
545
593
|
in a real Kimi host session, but only when the bridge itself ran; config
|
|
546
594
|
validation alone cannot prove that the hook is live.
|
|
547
|
-
The
|
|
595
|
+
The release adds a focused real-Windows Core gate for Issue #7, but native
|
|
548
596
|
cmd/PowerShell execution through every harness and general concurrent-subagent
|
|
549
597
|
safety remain explicit gaps. Later Guard branches (`git-guard`, `database-guard`,
|
|
550
598
|
`cloud-guard`) reuse the same protocol and compensation engine.
|
|
551
599
|
|
|
552
|
-
##
|
|
600
|
+
## guard-lab
|
|
553
601
|
|
|
554
|
-
The
|
|
602
|
+
The opt-in, offline honeytoken Lab uses disposable
|
|
555
603
|
projects and synthetic, non-secret markers. Its `clean`, `mock-positive`,
|
|
556
604
|
`mock-injection`, and `snapshot-positive` controls call no model and make no
|
|
557
605
|
external request. A bounded loopback observer records the fake Lab stub, bait
|
|
@@ -560,10 +608,10 @@ canary in selected output without retaining the raw value.
|
|
|
560
608
|
|
|
561
609
|
The user keeps the true controller and evidence outside the fixture shown to
|
|
562
610
|
the tested agent. Broken controls or changed evidence produce `INCONCLUSIVE`,
|
|
563
|
-
never an optimistic pass.
|
|
611
|
+
never an optimistic pass. The Lab cannot observe ordinary file
|
|
564
612
|
reads, prove remote transfer, universally block LLM calls, or resist a same-UID
|
|
565
613
|
adversary. Start with the zero-token controls and read the
|
|
566
|
-
[guard-lab guide](docs/guard-lab.md) before involving a real harness.
|
|
614
|
+
[guard-lab guide](docs/lab/guard-lab.md) before involving a real harness.
|
|
567
615
|
The built-in cases report `CALIBRATION_ONLY`. A separate manual
|
|
568
616
|
`injection-probe` treats bait contact as `EXPOSURE_OBSERVED`, and `compare`
|
|
569
617
|
accepts a mitigation result only after an effective unguarded baseline and a
|