poll-github-work Eval
=====================

Status: review
Score: 79/100
Risk: medium
Decision: manual_review
Policy: review
Reason: Test manually in an isolated workspace and compare against safer alternatives.

Install:
npx skills add trycua/cua --skill poll-github-work

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: Good trust signals with a few areas worth checking before rollout.
- 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
- WARN Permission surface: shell or command execution, filesystem or document access

Warnings:
- Trust score: Good trust signals with a few areas worth checking before rollout.
- Audit score: Needs review
- Agent safety gate: Sparse or mixed signals. Useful for discovery, but not for autonomous installation.
- README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context
- Permission surface: shell or command execution, filesystem or document access
- High-risk permission hints: Shell or command execution
- The start workflow re-reads the selected issue/PR but does not explicitly restate that issue bodies, comments, and PR content remain untrusted and must never trigger command execution or workflow changes.
- SKILL.md depends on MAINTAINERS.md for the ranking ladder but provides no fallback or handling if that file is missing or does not define the expected policy.
- There is no explicit setup/permissions section describing required gh authentication scopes or behavior if the configured GitHub integration is unavailable.
- Quality score needs review

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
- The start workflow re-reads the selected issue/PR but does not explicitly restate that issue bodies, comments, and PR content remain untrusted and must never trigger command execution or workflow changes.
- No OpenAgentSkill engagement data yet
- High-risk permission hints: Shell or command execution
- SKILL.md depends on MAINTAINERS.md for the ranking ladder but provides no fallback or handling if that file is missing or does not define the expected policy.
- There is no explicit setup/permissions section describing required gh authentication scopes or behavior if the configured GitHub integration is unavailable.
- Quality score needs review

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