Loading the registry…
Stress-test any artifact by spawning an Adversary agent (finds problems) then a Counterweight agent (calibrates findings). Use when the user says "adversarial review", "challenge this", "stress test this", "red team this", or wants a second opinion on a design or implementation.
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 -- 'cheapsteak/cheapsteak-agent-plugins (adversarial-review)'
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- 'cheapsteak/cheapsteak-agent-plugins (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.
v2.0.11
45 findings · 12.6s
v0.3.74
10 findings · 1.6s
v0.1.0
0 findings · 5.5s
v0.1.0
22 findings · 5.5s
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 · 1.1s
v0.71.0
No dependency manifest or lockfile was found in this artifact. What each scanner covers
0 findings · 0.4s
v2.3.8
No dependency manifest or lockfile was found in this artifact. What each scanner covers
0 findings · 0.2s
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 20, 2026 | Flagged50 | — | 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 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 77 findings across every scanner that examined this package.
Not reviewed is not the same as clean. Those 23 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.
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: AAK-AGENT-002 · Files: CLAUDE.md · reported by agent-audit-kit
The model could have called any of these a false positive and did not.
30 MANIFEST_MISSING_LICENSE
Files: /repo/plugins/git-flow/skills/rebase/SKILL.md, /repo/plugins/git-flow/skills/monitor-pr/SKILL.md, /repo/plugins/git-flow/skills/pr/SKILL.md and 27 more · reported by cisco-skill-scanner
13 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/plugins/git-flow/SKILL.md, /repo/plugins/web-tools/SKILL.md and 10 more · reported by cisco-skill-scanner
7 AAK-MARKETPLACE-001
Files: .claude-plugin/marketplace.json · reported by agent-audit-kit
1 AAK-SKILL-004
Files: plugins/git-flow/skills/pr/SKILL.md · reported by agent-audit-kit
1 LOW_ANALYZABILITY
Files: /repo/plugins/agent-workflow/skills/improvement-loop · reported by cisco-skill-scanner
1 SOCIAL_ENG_ANTHROPIC_IMPERSONATION
Files: /repo/plugins/skill-authoring-kit/skills/skill-authoring/SKILL.md · reported by cisco-skill-scanner
23 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: opt.nerlo-rules.nerlo-install-fetch-raw-then-run, AAK-HEALTHCARE-AI-004, opt.nerlo-rules.nerlo-install-run-bundled-artifact and 1 more · Files: /repo/plugins/computer-use/skills/drive-pc-apps/references/cua-driver-windows-setup.md, /repo/plugins/web-tools/skills/browse/references/cua-driver-setup.md, plugins/skill-authoring-kit/skills/skill-authoring/references/anthropic-skills-guide.md and 12 more · reported by nerlo-install-instruction, agent-audit-kit
Artifact can fetch and execute external code during installation.
The artifact includes installation instructions that fetch and execute external code, which could lead to arbitrary shell execution. Additionally, several high-severity findings relate to marketplace configuration and skill definitions. The artifact's low analyzability also hinders comprehensive security assessment.
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.