talk-review Eval
================

Status: review
Score: 65/100
Risk: medium
Decision: manual_review
Policy: review
Reason: Test manually in an isolated workspace and compare against safer alternatives.

Install:
npx skills add riwonswain-ovo/OfferLoop --skill talk-review

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: Sparse or mixed signals. Useful for discovery, but not for autonomous installation.
- PASS License clarity: MIT
- WARN Permission surface: network or browser access, database 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.
- Permission surface: network or browser access, database access
- ASR and resume content are untrusted inputs; although the workflow requires user confirmation and preserves uncertainty, SKILL.md does not explicitly state that instructions embedded in ASR/resume files must never be treated as commands. This is a minor prompt-injection hardening gap.
- The skill depends on hidden OfferLoop runtime files and scripts; outside that exact environment, operation may fail without a clear fallback beyond routing to --setup.
- Low GitHub adoption signal
- Quality score needs review
- GitHub adoption: 13 GitHub stars
- Stars/forks activity: 13 stars, 0 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
- ASR and resume content are untrusted inputs; although the workflow requires user confirmation and preserves uncertainty, SKILL.md does not explicitly state that instructions embedded in ASR/resume files must never be treated as commands. This is a minor prompt-injection hardening gap.
- The skill depends on hidden OfferLoop runtime files and scripts; outside that exact environment, operation may fail without a clear fallback beyond routing to --setup.
- Quality score needs review
- GitHub adoption: 13 GitHub stars
- Stars/forks activity: 13 stars, 0 forks; issue activity unavailable in current metadata

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