lld-reviewer Eval report.

Validation plan

What the agent should do next

1. 1Inspect repository, README/SKILL.md, license, and recent commits before production use.
2. 2Install in an isolated workspace or sandbox with no production secrets available.
3. 3Run the smallest representative task and record files touched, commands run, network access, and outputs.
4. 4Compare the selected skill against at least one alternative when the eval status is review or failed.
5. 5Promote only after the agent reports a successful verification result and unresolved warnings are accepted.

Do not use when

Conditions that require another skill

• teams that need a vendor-supported SLA
• production agents without a repository review
• The skill instructs the agent to run python3 scripts (trace_lint.py, trace_build_rtm.py) from the repository. If the repository is not pinned or vetted, this could introduce arbitrary code execution risk.
• No OpenAgentSkill engagement data yet
• The LLD documents being reviewed are treated as input data, but the skill does not explicitly instruct the agent to ignore any instructions embedded inside those documents. A malicious or poorly formatted LLD could attempt prompt injection.
• Quality score needs review