Loading the registry…
Reconstruct how a chunk of agent work actually ran — which skills routed, what decided what, how many subagents fanned out on which models and why, retries, review rounds, and whether it matched the planned shape. Use when the user asks how a run worked, to audit the last run, why a route or model was chosen, whether it ran as expected, or for a retrospective on how the work could have been done better. Reads the railyard run log, not the code 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.
25 critical findings reported by cisco-skill-scanner, 3 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 -- 'novotnyllc/railyard (audit)'
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- 'novotnyllc/railyard (audit)' ~/.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
268 findings · 15.3s
v0.3.74
7 findings · 7.8s
v0.1.0
1 finding · 9.1s
v0.1.0
4 findings · 9.1s
v1.4.0
None of the entry points this scanner reads were found in this artifact. What each scanner covers
0 findings · 0.4s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.2s
v0.1.0
This scanner found nothing in this artifact that it assesses. What each scanner covers
0 findings · 1.1s
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 21, 2026 | Scan Halted | — | 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 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 280 findings across every scanner that examined this package. 22 of 25 findings rated critical by their scanner were among the dismissals.
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.
175 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: COMMAND_INJECTION_JS_CHILD_PROCESS, DATA_EXFIL_JS_FS_ACCESS, opt.nerlo-rules.nerlo-install-shell-inline-command · Files: /repo/plugins/railyard/skills/orchestrate/scripts/delivery-contracts.test.mjs, /repo/plugins/railyard/skills/oracle/scripts/ensure-oracle.test.mjs, /repo/plugins/railyard/skills/oracle/scripts/oracle-route.test.mjs and 11 more · reported by cisco-skill-scanner, nerlo-install-instruction
9 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: AAK-HEALTHCARE-AI-004, SOCIAL_ENG_VAGUE_DESCRIPTION, MANIFEST_MISSING_LICENSE · Files: docs/delivery-workflows.md, /repo/docs/SKILL.md, /repo/docs/agents/SKILL.md and 2 more · reported by agent-audit-kit, 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.
32 MANIFEST_MISSING_LICENSE
Files: /repo/plugins/railyard/skills/deliver/SKILL.md, /repo/plugins/railyard/skills/orchestrate/SKILL.md, /repo/plugins/railyard/skills/thermo-nuclear-review/SKILL.md and 29 more · reported by cisco-skill-scanner
22 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/plugins/railyard/skills/orchestrate/SKILL.md, /repo/SKILL.md, /repo/site/SKILL.md and 19 more · reported by cisco-skill-scanner
18 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/plugins/railyard/skills/oracle/scripts/oracle-route.mjs, /repo/plugins/railyard/hooks/dispatch-gate.js, /repo/plugins/railyard/hooks/railyard-retro.js and 5 more · reported by cisco-skill-scanner
4 LOW_ANALYZABILITY
Files: /repo, /repo/plugins/railyard/skills/cleanup-codex, /repo/plugins/railyard/skills/oracle and 1 more · reported by cisco-skill-scanner
3 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/plugins/railyard/skills/cleanup-codex/scripts/lib/process-evidence.mjs, /repo/plugins/railyard/hooks/merge-settlement-gate.js
Critical command injection and high data exfiltration risks identified.
Critical command injection vulnerabilities are present in `/repo/plugins/railyard/hooks/merge-settlement-gate.js` and `/repo/plugins/railyard/skills/cleanup-codex/scripts/lib/process-evidence.mjs`, enabling shell execution. The artifact also exhibits high-severity data exfiltration risks through file system access in multiple files, including `/repo/plugins/railyard/hooks/dispatch-gate.js` and `/repo/plugins/railyard/skills/oracle/scripts/oracle-route.mjs`. Further high-severity findings indicate low analyzability and potential credential access in `SKILL.md` files. Medium-severity network egress is also noted.
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.
2 AAK-HEALTHCARE-AI-004
Files: plugins/railyard/skills/deliver/SKILL.md, plugins/railyard/skills/orchestrate/SKILL.md · reported by agent-audit-kit
2 AAK-SKILL-005
Files: plugins/railyard/skills/setup/SKILL.md, plugins/railyard/skills/doctor/SKILL.md · reported by agent-audit-kit
2 DATA_EXFIL_JS_NETWORK
Files: /repo/site/src/config/marketplace.mjs · reported by cisco-skill-scanner
2 EXCESSIVE_FILE_COUNT
Files: /repo/site/., /repo/. · reported by cisco-skill-scanner
2 FILE_MAGIC_MISMATCH
Files: /repo/site/src/pages/sitemap.xml.ts · reported by cisco-skill-scanner
2 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/UPSTREAM.md, /repo/plugins/railyard/skills/oracle/scripts/oracle-route.mjs · reported by nerlo-install-instruction
1 AAK-LEGAL-002
Files: site/package.json · reported by agent-audit-kit
1 AAK-SKILL-004
Files: plugins/railyard/skills/doctor/SKILL.md · reported by agent-audit-kit
1 HIDDEN_DATA_FILE
Files: /repo/plugins/railyard/.codex-plugin/plugin.json · reported by cisco-skill-scanner
1 opt.nerlo-rules.nerlo-hardcoded-external-egress
Files: /repo/site/src/config/marketplace.mjs · reported by nerlo-behavioral
1 opt.nerlo-rules.nerlo-install-shell-inline-command
Files: /repo/plugins/railyard/skills/oracle/scripts/reset-browser-profile.mjs · reported by nerlo-install-instruction
Showing 25 of 28; the rest are in the per-scanner reports above.