Warnings

• The skill depends on several Python scripts and local modules, but SKILL.md does not document installation steps, required dependencies, or the exact validate.py invocation command.
• It reads untrusted JSON artifacts from work_dir and may perform optional web research; there is no explicit note that work_dir evidence files must be treated as data, not as instructions.
• Quality score needs review

Method

This report combines public metadata, AI review output, repository freshness, install readiness, OpenAgentSkill events, quality scoring, trust checks, and the agent safety gate. It is not a full source-code security review.

Warnings

• The skill depends on several Python scripts and local modules, but SKILL.md does not document installation steps, required dependencies, or the exact validate.py invocation command.
• It reads untrusted JSON artifacts from work_dir and may perform optional web research; there is no explicit note that work_dir evidence files must be treated as data, not as instructions.
• Quality score needs review

Method

This report combines public metadata, AI review output, repository freshness, install readiness, OpenAgentSkill events, quality scoring, trust checks, and the agent safety gate. It is not a full source-code security review.

Warnings

• The skill depends on several Python scripts and local modules, but SKILL.md does not document installation steps, required dependencies, or the exact validate.py invocation command.
• It reads untrusted JSON artifacts from work_dir and may perform optional web research; there is no explicit note that work_dir evidence files must be treated as data, not as instructions.
• Quality score needs review

Method

This report combines public metadata, AI review output, repository freshness, install readiness, OpenAgentSkill events, quality scoring, trust checks, and the agent safety gate. It is not a full source-code security review.

Warnings

• The skill depends on several Python scripts and local modules, but SKILL.md does not document installation steps, required dependencies, or the exact validate.py invocation command.
• It reads untrusted JSON artifacts from work_dir and may perform optional web research; there is no explicit note that work_dir evidence files must be treated as data, not as instructions.
• Quality score needs review

Method

This report combines public metadata, AI review output, repository freshness, install readiness, OpenAgentSkill events, quality scoring, trust checks, and the agent safety gate. It is not a full source-code security review.