gza-code-review-full Eval
=========================

Status: failed
Score: 57/100
Risk: high
Decision: do_not_auto_install
Policy: block
Reason: Trust score: Potentially useful, but at least one trust signal needs human inspection.

Install:
npx skills add mhawthorne/gza --skill gza-code-review-full

Required checks:
- PASS Task fit: Task wording matches this skill metadata.
- PASS Install path: Install handoff is available.
- PASS Install command safety: standard package or runtime install path
- FAIL Trust score: Potentially useful, but at least one trust signal needs human inspection.
- WARN Audit score: Needs review
- FAIL Agent safety gate: This skill should not be selected by an agent without explicit human security review.
- PASS License clarity: MIT
- FAIL Permission surface: secrets or environment access, shell or command execution

Warnings:
- Audit score: Needs review
- High-risk permission hints: Shell or command execution, Secrets or environment access
- Dependency or permission surface needs review
- Permission surface may require sandboxing
- Skill is highly specific to the gza codebase, limiting reusability for other projects.
- Allowed bash commands are constrained to safe patterns, but the skill does not explicitly warn about potential side effects of running tests or mypy (e.g., network access, resource usage).
- The SKILL.md does not include a 'Limitations' section explicitly, though the scope is implied.
- Low GitHub adoption signal
- Quality score needs review
- Permission surface needs review: secrets or environment access, shell or command execution
- GitHub adoption: 11 GitHub stars
- Stars/forks activity: 11 stars, 1 forks; issue activity unavailable in current metadata

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
- Skill is highly specific to the gza codebase, limiting reusability for other projects.
- High-risk permission hints: Shell or command execution, Secrets or environment access
- Dependency or permission surface needs review
- Permission surface may require sandboxing
- Allowed bash commands are constrained to safe patterns, but the skill does not explicitly warn about potential side effects of running tests or mypy (e.g., network access, resource usage).

URLs:
- Skill: https://www.openagentskill.com/skills/mhawthorne-gza-code-review-full
- Audit: https://www.openagentskill.com/skills/mhawthorne-gza-code-review-full/audit
- JSON: https://www.openagentskill.com/api/agent/evals?slug=mhawthorne-gza-code-review-full