audit Eval
==========

Status: failed
Score: 63/100
Risk: high
Decision: do_not_auto_install
Policy: block
Reason: Install path: No install command or repository handoff is available.

Install:


Required checks:
- PASS Task fit: Task wording matches this skill metadata.
- FAIL Install path: No install command or repository handoff is available.
- PASS Install command safety: standard package or runtime install path
- WARN Trust score: Potentially useful, but at least one trust signal needs human inspection.
- WARN Audit score: Needs review
- WARN Agent safety gate: Sparse or mixed signals. Useful for discovery, but not for autonomous installation.
- PASS License clarity: MIT
- FAIL Permission surface: shell or command execution, filesystem or document access

Warnings:
- Trust score: Potentially useful, but at least one trust signal needs human inspection.
- Audit score: Needs review
- Agent safety gate: Sparse or mixed signals. Useful for discovery, but not for autonomous installation.
- High-risk permission hints: Shell or command execution
- Dependency or permission surface needs review
- The tracked source changed or could not be synchronized. Review the current source before installing.
- Permission surface may require sandboxing
- The skill references an external script `codex-run.ts` (via `bun "$HOME/.claude/src/scripts/codex-run.ts"`) that is not part of the skill repository. This creates a dependency on the user's environment and could be a portability concern if the script is missing or modified.
- The `requires: mcp: context7` field in the frontmatter may be interpreted as a hard requirement, but the skill text clarifies it is optional and only used when configured. This could cause confusion for users without the MCP.
- Low GitHub adoption signal
- Quality score needs review
- Permission surface needs review: shell or command execution, filesystem or document access

Validation plan:
1. Inspect repository, README/SKILL.md, license, and recent commits before production use.
2. Install in an isolated workspace or sandbox with no production secrets available.
3. Run the smallest representative task and record files touched, commands run, network access, and outputs.
4. Compare the selected skill against at least one alternative when the eval status is review or failed.
5. Promote only after the agent reports a successful verification result and unresolved warnings are accepted.

Do not use when:
- teams that need a vendor-supported SLA
- production agents without a repository review
- Low GitHub adoption signal
- The skill references an external script `codex-run.ts` (via `bun "$HOME/.claude/src/scripts/codex-run.ts"`) that is not part of the skill repository. This creates a dependency on the user's environment and could be a portability concern if the script is missing or modified.
- High-risk permission hints: Shell or command execution
- Dependency or permission surface needs review
- The tracked source changed or could not be synchronized. Review the current source before installing.
- Permission surface may require sandboxing

URLs:
- Skill: https://www.openagentskill.com/skills/darkroomengineering-audit
- Audit: https://www.openagentskill.com/skills/darkroomengineering-audit/audit
- JSON: https://www.openagentskill.com/api/agent/evals?slug=darkroomengineering-audit