analyze-comparison-tests Eval
=============================

Status: failed
Score: 65/100
Risk: high
Decision: do_not_auto_install
Policy: block
Reason: Agent safety gate: This skill should not be selected by an agent without explicit human security review.

Install:
npx skills add microsoft/GitHub-Copilot-for-Azure --skill analyze-comparison-tests

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
- 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:
- Trust score: Potentially useful, but at least one trust signal needs human inspection.
- 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
- No explicit prompt-injection guardrail when reading trajectory artifacts; the agent should be instructed to treat all file contents as untrusted data and ignore embedded instructions.
- The SKILL.md does not document setup or limitations, such as requiring a checkout with the tests/ directory and the compare:collect npm script configured.
- The input JSON schema is only described in prose; an example or link to the compare:run output would make the expected input clearer.
- Quality score needs review
- Permission surface needs review: secrets or environment access, shell or command execution
- Dependency/runtime risk: command execution surface, credential or environment access
- Permission surface: secrets or environment access, shell or command execution

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
- No explicit prompt-injection guardrail when reading trajectory artifacts; the agent should be instructed to treat all file contents as untrusted data and ignore embedded instructions.
- No OpenAgentSkill engagement data yet
- High-risk permission hints: Shell or command execution, Secrets or environment access
- Dependency or permission surface needs review
- Permission surface may require sandboxing
- The SKILL.md does not document setup or limitations, such as requiring a checkout with the tests/ directory and the compare:collect npm script configured.

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