Loading the registry…
外挂 RAG 记忆库 second-brain 的复核与去重整理。当出现： - 召回结果（`brain-recall`）里条目带 `duplicate-candidate` 或 `stale:as-of` 标签 - PR 归并前的记忆复核 - 怀疑 brain 内容重复或陈旧 时调用此 Skill。
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.
4 critical findings reported by cisco-skill-scanner. The composite score alone does not reflect this — read the per-scanner reports below.
Claude Skills install to a single target, no runtime picker.
nerlo install -- 'woodragon/cc-plugins (brain-curate)'
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- 'woodragon/cc-plugins (brain-curate)' ~/.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
123 findings · 23.4s
v0.3.74
16 findings · 17.6s
v0.1.0
1 finding · 5.1s
v0.1.0
2 findings · 5.1s
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 · 0.9s
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 21, 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 142 findings across every scanner that examined this package. None of the 4 findings rated critical by their scanner were dismissed.
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.
20 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: LOW_ANALYZABILITY, YARA_prompt_injection_unicode_steganography, DATA_EXFIL_NETWORK_REQUESTS and 3 more · Files: /repo/plugins/ppt-press/assets/scaffold/tests/ppt, /repo/plugins/deep-research/tests/test_render.py, /repo/plugins/deep-research/tests/test_harvest.py and 4 more · reported by cisco-skill-scanner, agent-audit-kit
3 Agent instruction file — The match is in a file that instructs an AI coding agent — a CLAUDE.md or similar. It is documentation of intent, and our own check confirmed it is not part of what gets installed.
Rules: AAK-AGENT-003, TOOL_ABUSE_UNDECLARED_NETWORK · Files: CLAUDE.md, /repo/repo/CLAUDE.md, /repo/plugins/deep-research/repo/plugins/deep-research/CLAUDE.md · reported by agent-audit-kit, cisco-skill-scanner
These findings are in files this artifact installs and are not placeholder values. No false-positive basis can be corroborated for such a finding, so this review never dismisses one; they were not sent to the model and stand at their scanner's severity.
29 MANIFEST_MISSING_LICENSE
Files: /repo/plugins/doc-gate/skills/doc-maintenance/SKILL.md, /repo/plugins/ppt-press/skills/ppt-deploy/SKILL.md, /repo/plugins/ppt-press/skills/ppt-init/SKILL.md and 26 more · reported by cisco-skill-scanner
26 DATA_EXFIL_NETWORK_REQUESTS
Files: /repo/plugins/deep-research/scripts/harvest_clients/base.py, /repo/plugins/deep-research/scripts/harvest_fetch/__init__.py, /repo/plugins/deep-research/scripts/harvest_search/__init__.py · reported by cisco-skill-scanner
17 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/plugins/doc-gate/SKILL.md, /repo/plugins/guardrails/SKILL.md and 14 more · reported by cisco-skill-scanner
9 AAK-MARKETPLACE-001
Files: .claude-plugin/marketplace.json · reported by agent-audit-kit
8 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/plugins/ppt-press/assets/scaffold/lib/manifest.js, /repo/plugins/ppt-press/assets/scaffold/src/integrations/manifest-gen.ts
Critical risks: system modification, command injection, and credential exposure
The artifact contains critical findings related to system modification capabilities in `plan-source.sh` and command injection vulnerabilities in `list-decks.js`. It also exhibits high-severity risks including potential file system access, execution of arbitrary commands, and the presence of credentials in `dispatch-capability-guard.sh` and `motion.min.js`. Additionally, the artifact may perform network egress after accessing secrets and contains code that could lead to infinite loops.
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.
6 RESOURCE_ABUSE_INFINITE_LOOP
Files: /repo/plugins/deep-research/scripts/harvest_clients/anthropic.py, /repo/plugins/deep-research/scripts/harvest_clients/base.py · reported by cisco-skill-scanner
4 AAK-SECRET-004
Files: plugins/ppt-press/assets/scaffold/public/assets/motion.min.js, plugins/dispatch-contract/hooks/dispatch-capability-guard.sh · reported by agent-audit-kit
4 FIND_EXEC_PATTERN
Files: /repo/plugins/deep-research/scripts/create-research-project.sh · reported by cisco-skill-scanner
4 YARA_prompt_injection_unicode_steganography
Files: /repo/plugins/deep-research/scripts/_sanitize.py · reported by cisco-skill-scanner
2 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/plugins/ppt-press/assets/scaffold/scripts/list-decks.js · reported by cisco-skill-scanner
2 FILE_MAGIC_MISMATCH
Files: /repo/plugins/plan-review/scripts/lib/manifest.sh · reported by cisco-skill-scanner
2 opt.nerlo-rules.nerlo-install-shell-inline-command
Files: /repo/plugins/guardrails/README.md · reported by nerlo-install-instruction
2 TOOL_ABUSE_SYSTEM_MODIFICATION
Files: /repo/plugins/plan-review/scripts/lib/plan-source.sh · reported by cisco-skill-scanner
1 AAK-LEGAL-002
Files: plugins/ppt-press/assets/scaffold/package.json · reported by agent-audit-kit
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner
1 LOW_ANALYZABILITY
Files: /repo/plugins/ppt-press · reported by cisco-skill-scanner
1 opt.nerlo-rules.nerlo-py-secret-to-network-egress
Files: /repo/plugins/deep-research/scripts/harvest_fetch/__init__.py · reported by nerlo-behavioral
Showing 25 of 36; the rest are in the per-scanner reports above.