Loading the registry…
Invoke for /audit-diff, "audit this PR", "audit the diff", "pre-merge audit", "second opinion on this change", or any pre-PR independent review of a Python diff against the project's GUIDELINES.md / CLAUDE.md / DESIGN.md. Scaffold-aware delta from the harness-level audit-diff skill: knows this plugin's project-brief paths and ships the 11-dimension framework (with two-axis mode flags, primary-dim rule, drift sweeps, meta-principles) as a static spec plus per-dimension checklists, a surface-detection script, a coordinator brief, and a report template. The skill itself does NOT spawn agents; the model or user reading this skill drives orchestration using whatever dispatch mechanism the runtime provides. Required (per global rules §3) before merging any PR that touches business logic, schema, or production behavior; skip only for docs-only / dependabot grouped-minor / single-file typo PRs. Distinct from general code review: this is the structural pre-merge gate, not freeform feedback. Do NOT trigger on changelog edits ("normalize CHANGELOG" → changelog-normalizer), scaffolding requests ("new repo" / "spin up project" → new-project), or release-flow phrasings ("cut a release" / "ship vX.Y.Z" / "tag and push" → release-helper).
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.
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/yuzh98/python-project-scaffold, 48 findings
Claude Skills install to a single target, no runtime picker.
nerlo install -- 'yuzh98/python-project-scaffold (audit-runner)'
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- 'yuzh98/python-project-scaffold (audit-runner)' ~/.claude/skills/
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
5 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
39 findings · 11.7s
v0.3.74
1 finding · 3.5s
v0.1.0
0 findings · 4.8s
v0.1.0
0 findings · 4.8s
v0.1.0
0 findings · 7.1s
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
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: 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 40 findings across every scanner that examined this package.
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.
16 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: SOCIAL_ENG_VAGUE_DESCRIPTION, MANIFEST_MISSING_LICENSE · Files: /repo/.github/SKILL.md, /repo/examples/SKILL.md, /repo/docs/adr/SKILL.md and 5 more · reported by cisco-skill-scanner
3 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, /repo/template/.github/SKILL.md, /repo/template/.github/ISSUE_TEMPLATE/SKILL.md · reported by 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.
9 MANIFEST_MISSING_LICENSE
Files: /repo/plugins/new-project/skills/new-project/SKILL.md, /repo/plugins/new-project/skills/release-helper/SKILL.md, /repo/plugins/new-project/skills/changelog-normalizer/SKILL.md and 6 more · reported by cisco-skill-scanner
5 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/template/SKILL.md, /repo/plugins/new-project/SKILL.md and 2 more · reported by cisco-skill-scanner
2 HIDDEN_DATA_FILE
Files: /repo/template/.pre-commit-config.yaml · reported by cisco-skill-scanner
1 AAK-MARKETPLACE-001
Files: .claude-plugin/marketplace.json · reported by agent-audit-kit
1 DATA_EXFIL_NETWORK_REQUESTS
Files: /repo/scripts/refresh_dev_deps.py · reported by cisco-skill-scanner
1 MANIFEST_DESCRIPTION_TOO_LONG
High-severity marketplace configuration and potential infinite loop risks.
High-severity findings indicate a potential infinite loop in `/repo/scripts/init-project.py` and a marketplace configuration issue in `.claude-plugin/marketplace.json`. Medium-severity findings show undeclared network egress and data exfiltration capabilities. These network capabilities could allow data to be sent externally.
Concern level assessed by the review: High. 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/new-project/skills/audit-runner/SKILL.md · reported by cisco-skill-scanner
1 RESOURCE_ABUSE_INFINITE_LOOP
Files: /repo/scripts/init-project.py · reported by cisco-skill-scanner
1 TOOL_ABUSE_UNDECLARED_NETWORK
Files: /repo/repo/CHANGELOG.md · reported by cisco-skill-scanner