clawsweeper

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The required workflow instructs the agent to search, query, and view GitHub issues and pull requests via gitcrawl and gh commands (e.g., lines 141-144, 180, 293-306, 338-345), which expose the agent to outsider-authored free text from issue bodies, comments, and PR descriptions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (medium risk: 0.30). The skill references an external GitHub repository clone in setup/refresh scripts (https://github.com/openclaw/clawsweeper.git), making it an unverifiable runtime external dependency under common/reputable unofficial provenance.