Loading the registry…
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.
16 critical findings reported by cisco-skill-scanner, agent-audit-kit, 14 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 -- samesake-workspace
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- samesake-workspace ~/.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.
v1.4.0
13 findings · 1.1s
v2.0.11
230 findings · 25.4s
v0.3.74
52 findings · 16.6s
v0.1.0
37 findings · 10.0s
v0.1.0
1 finding · 10.0s
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 · 1.6s
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 22, 2026 | Scan Halted | — | agentshield: completecisco-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 333 findings across every scanner that examined this package. 2 of 16 findings rated critical by their scanner were among the dismissals.
Not reviewed is not the same as clean. Those 8 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.
92 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: COMMAND_INJECTION_EVAL, opt.nerlo-rules.nerlo-js-secret-to-network-egress, LOW_ANALYZABILITY and 8 more · Files: /repo/examples/fashion-search/eval-enrichment.ts, /repo/examples/fashion-search/eval.ts, /repo/examples/fashion-search/gemini.ts and 52 more · reported by cisco-skill-scanner, nerlo-behavioral, nerlo-install-instruction and 1 more
5 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: agents-comment-injection-0, AAK-AGENT-005 · Files: CLAUDE.md · reported by agentshield, agent-audit-kit
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: AAK-GHA-IMMUTABLE-001 · Files: .github/workflows/ci.yml · reported by agent-audit-kit
1 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: FILE_MAGIC_MISMATCH · Files: /repo/examples/medusa-sync/src/fixtures.ts · 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.
79 DATA_EXFIL_JS_NETWORK
Files: /repo/apps/bom-quotation/server/src/gemini.ts, /repo/apps/bom-quotation/web/src/lib/api.ts, /repo/apps/ecommerce-assistant/src/seed.ts and 17 more · reported by cisco-skill-scanner
23 MANIFEST_MISSING_LICENSE
Files: /repo/.claude/skills/plandesk/SKILL.md, /repo/SKILL.md, /repo/.plandesk/SKILL.md and 20 more · reported by cisco-skill-scanner
21 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/.changeset/SKILL.md, /repo/rfcs/SKILL.md and 18 more · reported by cisco-skill-scanner
19 opt.nerlo-rules.nerlo-js-secret-to-network-egress
Files: /repo/apps/bom-quotation/server/src/gemini.ts, /repo/packages/cli/src/index.ts, /repo/packages/embed/src/embedder.ts and 5 more · reported by nerlo-behavioral
16 LOW_ANALYZABILITY
Files: /repo/packages/embed, /repo, /repo/packages/providers and 13 more · reported by cisco-skill-scanner
8 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: skills-missing-governance-commands/factory.md, skills-missing-governance-.claude/commands/plandesk.md, skills-missing-telemetry-.claude/commands/plandesk.md and 5 more · Files: commands/factory.md, .claude/commands/plandesk.md, commands/plandesk.md and 1 more · reported by agentshield
Critical shell execution and remote code execution risks identified.
The artifact contains multiple critical findings for command injection, allowing shell execution in `ecommerce-assistant/src/seed-from-sql.ts`, `scripts/pack-assert.ts`, and `scripts/release-drift-gates.ts`. Remote code execution via SQL is also present in `packages/cli/src/init.ts`. Additionally, high severity findings indicate potential credential access and network egress from various files, including `apps/playground/lib/blob.ts` and `packages/cli/src/init.ts`.
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.
11 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/apps/ecommerce-assistant/src/seed-from-sql.ts, /repo/scripts/pack-assert.ts, /repo/scripts/release-drift-gates.ts · reported by cisco-skill-scanner
7 AAK-LEGAL-002
Files: package.json, packages/mcp/package.json, apps/matcher/package.json and 4 more · reported by agent-audit-kit
5 AAK-SECRET-004
Files: scripts/publish-smoke.sh, packages/server/src/core/projects.ts, packages/server/src/core/parse.ts and 2 more · reported by agent-audit-kit
5 ASSET_PROMPT_INJECTION
Files: /repo/evals/adversarial-queries.json, /repo/evals/runs/2026-07-01T09-51-11-780Z-adversarial.json, /repo/evals/runs/2026-07-18T22-20-13-357Z-adversarial.json · reported by cisco-skill-scanner
4 HIDDEN_DATA_FILE
Files: /repo/.plandesk/config.json, /repo/.plandesk/skill.md, /repo/.changeset/config.json and 1 more · reported by cisco-skill-scanner
4 opt.nerlo-rules.nerlo-hardcoded-external-egress
Files: /repo/apps/bom-quotation/server/src/gemini.ts, /repo/apps/playground/scripts/r2-upload-smoke.ts, /repo/packages/embed/src/embedder.ts · reported by nerlo-behavioral
4 YARA_prompt_injection_unicode_steganography
Files: /repo/apps/ecommerce-assistant/data/seed.sql.gz · reported by cisco-skill-scanner
3 AAK-IPI-WILD-CORPUS-001
Files: evals/adversarial-queries.json, evals/runs/2026-07-01T09-51-11-780Z-adversarial.json, evals/runs/2026-07-18T22-20-13-357Z-adversarial.json · reported by agent-audit-kit
3 FILE_MAGIC_MISMATCH
Files: /repo/apps/playground/app/api/products/route.ts, /repo/bunfig.toml · reported by cisco-skill-scanner
2 AAK-SPLUNK-TOKLOG-001
Files: packages/cli/src/init.ts, packages/cli/src/index.ts · reported by agent-audit-kit
2 ARCHIVE_FILE_DETECTED
Files: /repo/apps/ecommerce-assistant/data/seed.sql.gz · reported by cisco-skill-scanner
2 EXCESSIVE_FILE_COUNT
Files: /repo/packages/server/., /repo/. · reported by cisco-skill-scanner
2 hooks-no-pretooluse
Files: settings.json, .claude/settings.json · reported by agentshield
2 permissions-no-block
Files: settings.json, .claude/settings.json · reported by agentshield
2 UNANALYZABLE_BINARY
Files: /repo/apps/ecommerce-assistant/data/seed.sql.gz · reported by cisco-skill-scanner
1 AAK-LLM-SQL-RCE-001
Files: packages/cli/src/init.ts · reported by agent-audit-kit
1 AAK-MCP-001
Files: .mcp.json · reported by agent-audit-kit
1 AAK-MCP-008
Files: .mcp.json · reported by agent-audit-kit
1 AAK-MCP-009
Files: .mcp.json · reported by agent-audit-kit
1 AAK-MCP-018
Files: packages/mcp/src/index.ts · reported by agent-audit-kit
1 AAK-MCP-ATTEST-001
Files: .mcp.json · reported by agent-audit-kit
1 AAK-MCP-SSRF-001
Files: packages/mcp/src/index.ts · reported by agent-audit-kit
1 AAK-OAUTH-008
Files: .mcp.json · reported by agent-audit-kit
1 AAK-TRUST-007
Files: .claude/settings.json · reported by agent-audit-kit
1 MANIFEST_INVALID_NAME
Files: /repo/.changeset/SKILL.md · reported by cisco-skill-scanner
Showing 25 of 63; the rest are in the per-scanner reports above.