guardrails-reviewer Eval
========================

Status: review
Score: 72/100
Risk: medium
Decision: manual_review
Policy: review
Reason: Require human approval before installing into a real workspace.

Install:
npx skills add TestAny-io/testany-agent-skills --skill guardrails-reviewer

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
- WARN Trust score: Potentially useful, but at least one trust signal needs human inspection.
- WARN Audit score: Needs review
- WARN Agent safety gate: Usable candidate, but the agent should surface permission and audit notes before installation.
- PASS License clarity: MIT
- PASS Permission surface: network or browser access

Warnings:
- Trust score: Potentially useful, but at least one trust signal needs human inspection.
- Audit score: Needs review
- Agent safety gate: Usable candidate, but the agent should surface permission and audit notes before installation.
- SKILL.md references `references/language-policy.md` and `references/workflow-hooks.md`, but those files are not present in the submitted skill directory, which may make some instructions incomplete.
- No explicit security guidance for handling potentially untrusted Guardrails documents; the skill should treat incoming documents as data and avoid executing any commands or following instructions embedded in them.
- The skill is mostly written in Chinese, while the agent interface is in English; this is acceptable due to the language policy, but could be clearer for non-Chinese users if language-policy.md is not available.
- Quality score needs review
- GitHub adoption: 81 GitHub stars
- Stars/forks activity: 81 stars, 23 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
- SKILL.md references `references/language-policy.md` and `references/workflow-hooks.md`, but those files are not present in the submitted skill directory, which may make some instructions incomplete.
- No OpenAgentSkill engagement data yet
- No explicit security guidance for handling potentially untrusted Guardrails documents; the skill should treat incoming documents as data and avoid executing any commands or following instructions embedded in them.
- The skill is mostly written in Chinese, while the agent interface is in English; this is acceptable due to the language policy, but could be clearer for non-Chinese users if language-policy.md is not available.
- Quality score needs review
- GitHub adoption: 81 GitHub stars

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