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.
12 critical findings reported by cisco-skill-scanner, agent-audit-kit. 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 -- fliwright
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- fliwright ~/.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
2 findings · 0.8s
v2.0.11
632 findings · 28.5s
v0.3.74
60 findings · 17.8s
v0.1.0
0 findings · 7.2s
v0.1.0
0 findings · 7.2s
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 · 0.9s
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 ·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 694 findings across every scanner that examined this package. None of the 12 findings rated critical by their scanner were dismissed.
Not reviewed is not the same as clean. Those 694 findings stand exactly as their scanners reported them, at full severity, as they would have without this review.
326 The review call did not complete.
Rules: COMMAND_INJECTION_JS_CHILD_PROCESS, AAK-TAINT-001, DATA_EXFIL_JS_FS_ACCESS and 19 more · Files: /repo/scripts/check-codex-plugin.mjs, /repo/scripts/install-codex-plugin-marketplace.mjs, /repo/scripts/reload-codex-plugin.mjs and 208 more · reported by cisco-skill-scanner, agent-audit-kit, agentshield
310 The review budget for this scan was already spent before these findings were reached.
Rules: HIDDEN_DATA_FILE, MANIFEST_MISSING_LICENSE, MANIFEST_INVALID_NAME and 1 more · Files: /repo/packages/fliwright-vitest/.fliwright/runs/2026-06-21T12-40-27-provides-timeline-native-fixtures/logs/events.jsonl, /repo/packages/fliwright-vitest/.fliwright/runs/2026-06-19T09-05-28-provides-timeline-native-fixtures/timeline.json, /repo/packages/fliwright-vitest/.fliwright/runs/2026-06-21T12-40-27-provides-an-aiRuntime-fixture-to-generated-tests/logs/events.jsonl and 299 more · reported by cisco-skill-scanner
58 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: HIDDEN_DATA_FILE · Files: /repo/packages/fliwright-vitest/.fliwright/ai/2026-06-21T13-03-06-provides-timeline-native-fixtures/provides_timeline-native_fixtures/ai-1/request.json, /repo/packages/fliwright-vscode/.DS_Store, /repo/packages/fliwright-mcp/.fliwright/ai/mcp-diagnosis/mcp_diagnosis/ai-1/meta.json and 55 more · reported by cisco-skill-scanner
Critical risks: command injection and data taint.
The artifact presents critical risks including command injection vulnerabilities in scripts like `check-codex-plugin.mjs` and `install-codex-plugin-marketplace.mjs`, allowing for shell execution. Data taint issues are present in `packages/fliwright-mcp/src/tools/generateTest.ts`, indicating potential for untrusted data processing. High severity findings also include numerous instances of file system access for data exfiltration and hidden executable scripts. Additionally, potential sensitive configuration exposure is noted in `.agents/plugins/marketplace.json` and `.claude/settings.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.