Loading the registry…
マージ済み PR から知見を抽出し ACE Playbook（docs/08-knowledge/）へ構造化エントリとして追記する
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.
15 critical findings reported by cisco-skill-scanner, agent-audit-kit, 6 of them in the installed artifact. 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 -- 'feel-flow/ff-dev-toolkit (ace-curate)'
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- 'feel-flow/ff-dev-toolkit (ace-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
642 findings · 33.4s
v0.3.74
8 findings · 11.6s
v0.1.0
0 findings · 7.7s
v0.1.0
28 findings · 7.7s
v1.4.0
None of the entry points this scanner reads were found in this artifact. What each scanner covers
0 findings · 0.3s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.2s
v0.1.0
This scanner found nothing in this artifact that it assesses. What each scanner covers
0 findings · 1.3s
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 678 findings across every scanner that examined this package. 9 of 15 findings rated critical by their scanner were among the dismissals.
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.
359 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: COMMAND_INJECTION_JS_CHILD_PROCESS, COMPOUND_FIND_EXEC, AAK-MCP-STDIO-CMD-INJ-002 and 5 more · Files: /repo/plugins/ff-dev-toolkit/docs-template/scripts/ace/shell-hooks.test.ts, /repo/plugins/ff-dev-toolkit/tests/ace-scripts-mirror/verify.sh, /repo/plugins/ff-dev-toolkit/tests/lib/tree-state.sh and 15 more · reported by cisco-skill-scanner, agent-audit-kit
150 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-SKILL-003, SOCIAL_ENG_VAGUE_DESCRIPTION, MANIFEST_MISSING_LICENSE and 1 more · Files: plugins/ff-dev-toolkit/docs-template/.github/skills/error-handling-standards/SKILL.md, /repo/plugins/ff-dev-toolkit/tests/cli-registry-completeness/SKILL.md, /repo/plugins/ff-dev-toolkit/tests/multi-agent-revision-guard/SKILL.md and 73 more · 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.
47 MANIFEST_MISSING_LICENSE
Files: /repo/plugins/ff-dev-toolkit/skills/ace-curate/SKILL.md, /repo/plugins/ff-dev-toolkit/skills/multi-implement/SKILL.md, /repo/plugins/ff-dev-toolkit/skills/harness-review/SKILL.md and 44 more · reported by cisco-skill-scanner
42 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/plugins/ff-dev-toolkit/docs-template/scripts/ace/ace-refine-report.ts, /repo/plugins/ff-dev-toolkit/docs-template/scripts/ace/ace-reuse-report.ts, /repo/plugins/ff-dev-toolkit/docs-template/scripts/ace/check-archive-links.ts and 7 more · reported by cisco-skill-scanner
27 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/CHANGELOG.md, /repo/plugins/ff-dev-toolkit/docs-template/05-operations/deployment/ace-autonomous.md, /repo/plugins/ff-dev-toolkit/docs-template/05-operations/deployment/multi-cli-review-orchestration.md and 3 more · reported by nerlo-install-instruction
25 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/plugins/ff-dev-toolkit/docs-template/SKILL.md, /repo/plugins/ff-dev-toolkit/mcp/SKILL.md and 22 more · reported by cisco-skill-scanner
5
Critical command injection and file system access risks
The artifact contains critical command injection vulnerabilities via `eval` and `Function` constructor in `/repo/plugins/ff-dev-toolkit/mcp/dist/index.js`, which could lead to arbitrary shell execution. It also exhibits high-severity file system access capabilities in multiple files within `/repo/plugins/ff-dev-toolkit/docs-template/scripts/ace`. Additionally, the artifact has capabilities for network egress. These findings warrant immediate attention.
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.
Files: /repo/plugins/ff-dev-toolkit/docs-template/03-implementation, /repo/plugins/ff-dev-toolkit/docs-template/scripts/ace, /repo/plugins/ff-dev-toolkit/mcp and 2 more · reported by cisco-skill-scanner
4 COMMAND_INJECTION_EVAL
Files: /repo/plugins/ff-dev-toolkit/mcp/dist/index.js · reported by cisco-skill-scanner
4 DATA_EXFIL_JS_NETWORK
Files: /repo/plugins/ff-dev-toolkit/docs-template/03-implementation/templates/typescript/q1-http-api-client.skeleton.ts · reported by cisco-skill-scanner
2 COMMAND_INJECTION_JS_FUNCTION_CONSTRUCTOR
Files: /repo/plugins/ff-dev-toolkit/mcp/dist/index.js · reported by cisco-skill-scanner
2 COMMAND_INJECTION_USER_INPUT
Files: /repo/plugins/ff-dev-toolkit/scripts/multi-agent.sh · reported by cisco-skill-scanner
2 EXCESSIVE_FILE_COUNT
Files: /repo/plugins/ff-dev-toolkit/docs-template/., /repo/. · reported by cisco-skill-scanner
2 FIND_EXEC_PATTERN
Files: /repo/CHANGELOG.md, /repo/SKILL.md · reported by cisco-skill-scanner
1 AAK-IPI-WILD-CORPUS-001
Files: plugins/ff-dev-toolkit/docs-template/04-quality/TESTING.md · reported by agent-audit-kit
1 AAK-MARKETPLACE-001
Files: .claude-plugin/marketplace.json · reported by agent-audit-kit
1 AAK-MCP-018
Files: plugins/ff-dev-toolkit/mcp/src/index.ts · reported by agent-audit-kit
1 AAK-MCP-ATTEST-001
Files: plugins/ff-dev-toolkit/.mcp.json · reported by agent-audit-kit
1 AAK-MCP-STDIO-LAUNCHER-INJECT-001
Files: plugins/ff-dev-toolkit/.mcp.json · reported by agent-audit-kit
1 LAZY_LOAD_DEEP_NESTING
Files: /repo/plugins/ff-dev-toolkit/docs-template/05-operations/deployment/SKILL.md · reported by cisco-skill-scanner
1 opt.nerlo-rules.nerlo-install-shell-inline-command
Files: /repo/CHANGELOG.md · reported by nerlo-install-instruction
Showing 25 of 59; the rest are in the per-scanner reports above.