Loading the registry…
Review doctrine for the class of defect authors are systematically blind to — code that is correct on its own terms but does not do what its own documentation, config, comments or project rules claim it does. Use this skill whenever reviewing a diff, a pull request, or a branch; before committing; when asked to check, audit, critique or sign off on changes; or when acting as a merge gate. Names the recurring defect classes (claims-vs-enforcement, dead-declaration, carve-out-without-negative-test, coverage-gap, doctrine-contradiction, unverified-negative, gate-that-cannot-fail) and how to detect each. Complements correctness review (authorization, scoping, query safety, tests); it does not replace it. Code QUALITY — duplication, redundant state, efficiency, a fix at the wrong level — is the separate, advisory `quality-pass` skill, which runs after this one.
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.
5 critical findings reported by cisco-skill-scanner. The composite score alone does not reflect this — read the per-scanner reports below.
This artifact ships from 2 sources and their verdicts differ. The worst is github (Flagged). Installing from a cleaner source does not mean the others are safe — check the source you actually install from.
github: https://github.com/fmanimashaun/claude-skills, 314 findings
Claude Skills install to a single target, no runtime picker.
nerlo install -- 'fmanimashaun/claude-skills (code-review)'
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- 'fmanimashaun/claude-skills (code-review)' ~/.claude/skills/
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
6 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.
v1.4.0
14 findings · 1.0s
v2.0.11
135 findings · 37.1s
v0.3.74
10 findings · 38.5s
v0.1.0
2 findings · 14.8s
v0.1.0
6 findings · 14.8s
v0.1.0
0 findings · 16.9s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.1s
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: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicablenerlo-multi-source: complete | 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 167 findings across every scanner that examined this package. None of the 5 findings rated critical by their scanner were dismissed.
Not reviewed is not the same as clean. Those 112 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.
2 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: opt.nerlo-rules.nerlo-install-run-bundled-artifact · Files: /repo/docs/harness-doctrine.md · reported by nerlo-install-instruction
1 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: TOOL_ABUSE_UNDECLARED_NETWORK · Files: /repo/repo/AGENTS.md · reported by cisco-skill-scanner
1 CI or editor configuration — The match is in build, CI or editor configuration, confirmed by our own check to be outside the installed artifact.
Rules: MANIFEST_INVALID_NAME · Files: /repo/.github/SKILL.md · reported by cisco-skill-scanner
The model could have called any of these a false positive and did not.
32 DATA_EXFIL_NETWORK_REQUESTS
Files: /repo/plugins/design-flow/scripts/asset_plan.py, /repo/plugins/design-flow/scripts/generate_asset.py · reported by cisco-skill-scanner
7 BINARY_FILE_DETECTED
Files: /repo/dist/fidara-design.skill, /repo/dist/quality-pass.skill, /repo/dist/rails-8.skill and 4 more · reported by cisco-skill-scanner
6 UNANALYZABLE_BINARY
Files: /repo/dist/quality-pass.skill, /repo/dist/fidara-design.skill, /repo/dist/code-review.skill and 3 more · reported by cisco-skill-scanner
2 COMMAND_INJECTION_EVAL
Files: /repo/plugins/design-flow/scripts/pen_to_svg.py · reported by cisco-skill-scanner
2 opt.nerlo-rules.nerlo-py-secret-to-network-egress
Files: /repo/plugins/design-flow/scripts/asset_plan.py, /repo/plugins/design-flow/scripts/generate_asset.py · reported by nerlo-behavioral
2 RESOURCE_ABUSE_INFINITE_LOOP
87 The review call did not complete.
Rules: hooks-no-pretooluse, agents-oversized-prompt-agents/release-manager.md, YARA_capability_inflation_generic and 19 more · Files: settings.json, agents/release-manager.md, /repo/SKILL.md and 52 more · reported by agentshield, cisco-skill-scanner, agent-audit-kit and 1 more
25 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: YARA_coercive_injection_generic, AAK-MARKETPLACE-001, PROMPT_INJECTION_CONCEALMENT and 8 more · Files: /repo/SKILL.md, /repo/dist/fidara-design.skill, /repo/skills/fidara-design/references/SKILL.md and 11 more · reported by cisco-skill-scanner, agent-audit-kit, agentshield
Critical command injection and data exfiltration risks.
The artifact contains critical command injection vulnerabilities in `pen_to_svg.py`, enabling shell execution. Multiple other critical findings exist across various Python scripts, indicating potential for high-impact operations. High-severity findings also reveal secret exposure and network egress of sensitive data. Additionally, numerous medium-severity findings indicate undeclared network requests and potential data exfiltration.
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/scripts/issue_graph.py, /repo/scripts/lint_markdown_code.py · reported by cisco-skill-scanner
Showing 13 of 13; the rest are in the per-scanner reports above.