Loading the registry…
A curated library of Claude Code Agent Skills covering the full software lifecycle, with orchestrator-routed activation that scales past the skill-listing budget.
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.
3 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/swestash/swe-workflow-skills, 962 findings
Claude Skills install to a single target, no runtime picker.
nerlo install -- swe-workflow-skills
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- swe-workflow-skills ~/.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
3 findings · 0.8s
v2.0.11
921 findings · 65.8s
v0.3.74
33 findings · 21.0s
v0.1.0
0 findings · 10.1s
v0.1.0
3 findings · 10.1s
v0.1.0
0 findings · 13.8s
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 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 960 findings across every scanner that examined this package. None of the 3 findings rated critical by their scanner were dismissed.
Not reviewed is not the same as clean. Those 960 findings stand exactly as their scanners reported them, at full severity, as they would have without this review.
960 The review call did not complete.
Rules: COMMAND_INJECTION_JS_CHILD_PROCESS, AAK-MARKETPLACE-001, SECRET_CONNECTION_STRING and 15 more · Files: /repo/bin/cli.mjs, /repo/scripts/build-plugins.mjs, .claude-plugin/marketplace.json and 616 more · reported by cisco-skill-scanner, agent-audit-kit, agentshield and 1 more
Critical command injection and credential exposure risks.
The artifact contains critical command injection vulnerabilities in `/repo/bin/cli.mjs` and `/repo/scripts/build-plugins.mjs`, which could lead to shell execution. Additional critical findings are present in `/repo/evals/routing.py` and `/repo/evals/run.py`. High severity findings indicate potential exposure of secrets in `plugins/*/skills/*/evals/evals.json` and sensitive data in `plugins/*/skills/*/templates/schema.md`. Multiple high severity findings also relate to `.claude-plugin/marketplace.json`.
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.
Showing 23 of 23; the rest are in the per-scanner reports above.