provenance Eval
===============

Status: review
Score: 76/100
Risk: medium
Decision: manual_review
Policy: review
Reason: Require human approval before installing into a real workspace.

Install:
npx skills add anbeime/skill --skill provenance

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: Usable candidate, but the agent should surface permission and audit notes before installation.
- WARN License clarity: Unknown
- PASS Permission surface: database access

Warnings:
- Trust score: Good trust signals with a few areas worth checking before rollout.
- Audit score: Needs review
- Agent safety gate: Usable candidate, but the agent should surface permission and audit notes before installation.
- README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context
- License clarity: Unknown
- License is unclear
- Repository license is unknown; compliance cannot be fully verified.
- SKILL.md describes vector index and query API outputs, but the provided script only generates trace.jsonl and trace_summary.json; no evidence of vector index or query API implementation.
- Dependencies mention Qdrant and MCP, but the script claims to run offline; the actual vector storage integration is unclear.
- 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
- Repository license is unknown; compliance cannot be fully verified.
- No OpenAgentSkill engagement data yet
- License is unclear
- SKILL.md describes vector index and query API outputs, but the provided script only generates trace.jsonl and trace_summary.json; no evidence of vector index or query API implementation.
- Dependencies mention Qdrant and MCP, but the script claims to run offline; the actual vector storage integration is unclear.
- Quality score needs review

URLs:
- Skill: https://www.openagentskill.com/skills/anbeime-provenance
- Audit: https://www.openagentskill.com/skills/anbeime-provenance/audit
- JSON: https://www.openagentskill.com/api/agent/evals?slug=anbeime-provenance