Loading the registry…
以 PRD 為核心的規格驅動開發工作流——為 AI coding agent 設計的十步流程（skills / rules / hooks / templates），npx specrail init 一鍵導入專案
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.
5 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/chu1999tw/specrail, 122 findings
Claude Skills install to a single target, no runtime picker.
nerlo install -- specrail
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- specrail ~/.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
10 findings · 1.2s
v2.0.11
111 findings · 6.6s
v0.3.74
1 finding · 1.4s
v0.1.0
0 findings · 2.9s
v0.1.0
0 findings · 2.9s
v0.1.0
0 findings · 6.3s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.1s
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 22, 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 122 findings across every scanner that examined this package. None of the 5 findings rated critical by their scanner were dismissed.
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.
40 MANIFEST_MISSING_LICENSE
Files: /repo/.claude/skills/prd/SKILL.md, /repo/.claude/skills/wireframe/SKILL.md, /repo/.claude/skills/tutorial-sync/SKILL.md and 37 more · reported by cisco-skill-scanner
33 HIDDEN_DATA_FILE
Files: /repo/.agents/skills/intake/references/document-analysis.md, /repo/.agents/agents/contract-reviewer.md, /repo/.agents/skills/tech-design/SKILL.md and 30 more · reported by cisco-skill-scanner
22 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/.claude/skills/tech-design/SKILL.md, /repo/.claude/skills/lock-flow/SKILL.md, /repo/.agents/skills/tech-design/SKILL.md and 19 more · reported by cisco-skill-scanner
6 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/bin/specrail.js · reported by cisco-skill-scanner
5 PATH_TRAVERSAL_ATTEMPT
Files: /repo/.claude/skills/prd/SKILL.md, /repo/.claude/skills/tech-design/SKILL.md, /repo/.claude/skills/uat/SKILL.md and 2 more · reported by cisco-skill-scanner
4 HIDDEN_EXECUTABLE_SCRIPT
Files: /repo/.agents/hooks/gate-flow-lock.sh, /repo/.agents/hooks/gate-bash-writes.sh, /repo/.agents/hooks/tutorial-sync-reminder.sh and 1 more · reported by cisco-skill-scanner
2 hooks-no-stop-hooks
Files: settings.json, .claude/settings.json · reported by agentshield
2 permissions-no-block
Files: settings.json, .claude/settings.json · reported by agentshield
1 AAK-SUPPLY-004
Files: package.json · reported by agent-audit-kit
1 agents-no-model-.claude/agents/contract-reviewer.md
Files: .claude/agents/contract-reviewer.md · reported by agentshield
1 agents-no-model-.claude/agents/rd-feasibility.md
Files: .claude/agents/rd-feasibility.md · reported by agentshield
1 agents-no-model-.claude/agents/spec-critic.md
Files: .claude/agents/spec-critic.md · reported by agentshield
1 agents-no-model-agents/contract-reviewer.md
Files: agents/contract-reviewer.md · reported by agentshield
1 agents-no-model-agents/rd-feasibility.md
Files: agents/rd-feasibility.md · reported by agentshield
1 agents-no-model-agents/spec-critic.md
Files: agents/spec-critic.md · reported by agentshield
1 MANIFEST_INVALID_NAME
Files: /repo/.docs/SKILL.md · reported by cisco-skill-scanner
Critical path traversal and high-risk script execution identified.
The artifact contains critical path traversal vulnerabilities in multiple skill definition files, which could allow access to restricted directories. Additionally, several hidden executable scripts are present in agent hooks, enabling shell execution. The artifact also includes JavaScript code that performs file system access, indicating potential data exfiltration capabilities.
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.