Loading the registry…
Audit repo-local, current-project, or user-global Codex context for stale, pending, missing, or risky freshness metadata. Use when the user asks to review context freshness, stale context, outdated decisions, pending distillation, pending promotion, or whether context should be revalidated before reuse. Current-project audits require `.tkn/codex-context.yaml` to resolve in the private registry; marker creation alone is not a trigger.
Claude Skills are markdown + scripts loaded into Claude Code; scanned with the same pipeline.
We found this by crawling public sources and nobody has attested to it. That is how most of the registry gets here, and it is not a mark against the artifact — it only means no authenticated act of publication is on record. An artifact can be the vendor's own and still appear here.
Claude Skills install to a single target, no runtime picker.
nerlo install -- 'tuckn/tkn-codex-plugins (audit-context-freshness)'
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- 'tuckn/tkn-codex-plugins (audit-context-freshness)' ~/.claude/skills/
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
4 of 11 scanners examined this package. The rest do not apply to it — language, ecosystem and packaging decide which analyzers can say anything, and a scanner that cannot examine an artifact reports nothing rather than passing it.
v2.0.11
34 findings · 13.7s
v0.3.74
1 finding · 5.8s
v0.1.0
0 findings · 4.6s
v0.1.0
0 findings · 4.6s
v1.4.0
None of the entry points this scanner reads were found in this artifact. What each scanner covers
0 findings · 0.2s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.1s
v0.1.0
This scanner found nothing in this artifact that it assesses. What each scanner covers
0 findings · 1.0s
No report in this scan: govulncheck, osv-scanner, trivy, trivy_image.
1 scan on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Aug 20, 2026 | Scan Halted | — | agentshield ·n/a: not applicablecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicablenerlo-multi-source ·n/a: not applicable | rejected |
Findings in files this artifact installs stand as reported; a model re-read the rest and said which ones it believes are false positives. This is a second opinion published beside the evidence, not a correction to it: the per-scanner reports above are unchanged, every dismissed finding is still listed there at its original severity, and the score and the Flagged badge are computed from those raw severities alone. Nothing below moved them.
Out of 35 findings across every scanner that examined this package.
Not reviewed is not the same as clean. Those 21 findings stand exactly as their scanners reported them, at full severity, as they would have without this review.
Two keys had to turn. The model had to name a reason from a fixed list of six, and a deterministic check of ours — over which files this artifact actually installs — had to independently agree. Anything it could not corroborate is in “not reviewed” above, at full severity.
4 Test or fixture file — The match is in a test or fixture. Our own check confirmed the file is not part of what gets installed.
Rules: GLOB_HIDDEN_FILE_TARGETING, MANIFEST_MISSING_LICENSE · Files: /repo/plugins/tkn-codex-context-engineering/skills/write-global-working-context/tests/test_write_global_working_context.py, /repo/plugins/tkn-codex-context-engineering/tests/fixtures/SKILL.md · reported by cisco-skill-scanner
The model could have called any of these a false positive and did not.
5 RESOURCE_ABUSE_INFINITE_LOOP
Files: /repo/plugins/tkn-codex-context-engineering/skills/plan-context-rebuild-from-chats/scripts/materialize_context_rebuild_shadow.py, /repo/plugins/tkn-codex-context-engineering/lib/tkn_codex_context/session_notes.py · reported by cisco-skill-scanner
3 HIDDEN_DATA_FILE
Files: /repo/plugins/tkn-codex-context-engineering/.codex-plugin/plugin.json, /repo/.agents/plugins/marketplace.json · reported by cisco-skill-scanner
1 AAK-MARKETPLACE-001
Files: .agents/plugins/marketplace.json · reported by agent-audit-kit
1 HIDDEN_EXECUTABLE_SCRIPT
Files: /repo/.local/normalize_state_note_paths.py · reported by cisco-skill-scanner
21 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: SOCIAL_ENG_VAGUE_DESCRIPTION, MANIFEST_MISSING_LICENSE · Files: /repo/SKILL.md, /repo/plugins/tkn-codex-context-engineering/SKILL.md, /repo/plugins/tkn-codex-context-engineering/skills/search-all-codex-chats/references/SKILL.md and 15 more · reported by cisco-skill-scanner
Critical findings in chat processing scripts, hidden executables, and resource abuse.
Critical findings from the 'bearer' scanner are present in Python scripts responsible for initializing, planning, and refreshing project context from chats, indicating potential sensitive data exposure or insecure operations. High severity findings include a hidden executable script at `/repo/.local/normalize_state_note_paths.py`, which could allow unexpected shell execution. Additionally, multiple Python scripts related to chat context processing and rebuilding contain high severity resource abuse vulnerabilities, potentially leading to infinite loops. Another high finding points to a marketplace configuration issue in `.agents/plugins/marketplace.json`.
Concern level assessed by the review: Critical. This is the review's scale, not the registry badge.
Reviewed by gemini-2.5-flash. The model sees the findings, not your code, and cannot change a score.