Loading the registry…
The procedure for adversarially reviewing a change — resolve what is under review, attack it, return a verdict. Its job is to break the change, not to approve it. Loaded by the `adversary` subagent when the review gate or Phase 5 spawns it, and usable directly on any diff.
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 -- 'vavly/skills (adversarial-review)'
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- 'vavly/skills (adversarial-review)' ~/.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.
v1.4.0
2 findings · 0.5s
v2.0.11
17 findings · 6.9s
v0.3.74
2 findings · 1.1s
v0.1.0
18 findings · 2.6s
v0.1.0
No source files this scanner can analyze were found in this artifact. What each scanner covers
0 findings · 2.6s
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
v0.71.0
No dependency manifest or lockfile was found in this artifact. What each scanner covers
0 findings · 0.2s
v2.3.8
No dependency manifest or lockfile was found in this artifact. What each scanner covers
0 findings · 0.1s
v0.71.0
No container image was published for this artifact. What each scanner covers
0 findings · 0.0s
vv1.6.0
No Go modules were found in this artifact. What each scanner covers
0 findings · 0.1s
1 scan on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Aug 21, 2026 | Flagged82 | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral ·n/a: not applicablenerlo-install-instruction: completecapslock ·n/a: not applicablenerlo-multi-source ·n/a: not applicabletrivy ·n/a: not applicableosv-scanner ·n/a: not applicabletrivy_image ·n/a: not applicablegovulncheck ·n/a: not applicable | completed |
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 39 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.
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: SOCIAL_ENG_VAGUE_DESCRIPTION, MANIFEST_INVALID_NAME, MANIFEST_MISSING_LICENSE · Files: /repo/.github/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.
18 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/plugins/spec-gate/README.md, /repo/plugins/spec-gate/skills/spec-driven/SKILL.md, /repo/plugins/spec-gate/skills/spec-driven/references/slicing.md and 2 more · reported by nerlo-install-instruction
9 MANIFEST_MISSING_LICENSE
Files: /repo/plugins/spec-gate/skills/spec-driven/SKILL.md, /repo/plugins/spec-gate/skills/adversarial-review/SKILL.md, /repo/plugins/spec-gate/skills/spec-gate-install/SKILL.md and 6 more · reported by cisco-skill-scanner
3 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/plugins/spec-gate/SKILL.md, /repo/plugins/spec-gate/skills/spec-driven/references/SKILL.md · reported by cisco-skill-scanner
2 FIND_EXEC_PATTERN
Files: /repo/plugins/spec-gate/test.sh · reported by cisco-skill-scanner
1 AAK-HEALTHCARE-AI-004
Files: plugins/spec-gate/skills/adversarial-review/SKILL.md · reported by agent-audit-kit
1 AAK-MARKETPLACE-001
Files: .claude-plugin/marketplace.json · reported by agent-audit-kit
Artifact includes shell execution and marketplace configuration issues
The artifact contains patterns indicative of shell execution within `/repo/plugins/spec-gate/test.sh`. Additionally, a high-severity finding related to marketplace configuration is present in `.claude-plugin/marketplace.json`. Multiple medium-severity findings indicate potential issues with permissions and pre-tool use hooks.
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.
1 hooks-no-pretooluse
Files: settings.json · reported by agentshield
1 permissions-no-block
Files: settings.json · reported by agentshield