evidence-hygiene Audit report.

Warnings

• Dependency or permission surface needs review
• Permission surface may require sandboxing
• Financial research output is not financial advice; require human review before any live investment decision
• The provided SKILL.md excerpt appears truncated mid-checklist at 'After ca', so the complete file may be missing the rest of the pre-screenshot checklist, HAR jq commands, filename conventions, and post-submission rotation guidance.
• The skill lacks an explicit safe operating boundary note reminding agents to only use this on authorized bug-bounty targets and not to bypass platform rules.
• The 'test-account passwords acceptable in screenshots' exception is risky if rotation is forgotten; it should be paired with a stronger warning or a recommendation to use disposable credentials that are already invalidated.
• Financial research output is not financial advice; require human review before any live investment decision.
• Quality score needs review
• Permission surface needs review: secrets or environment access, shell or command execution
• Dependency/runtime risk: command execution surface, credential or environment access
• Permission surface: secrets or environment access, shell or command execution

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.