bpa-rules

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

• Third-party content exposure detected (high risk: 1.00). The skill's workflow (SKILL.md) explicitly instructs the agent to fetch and read BPA rule files from user-provided paths or URLs (e.g., "If the user has existing rules, ask for the file path or URL and read them") and TMDL annotations support external rule file URLs (references/tmdl-annotations.md), and those remote rule definitions (including FixExpression actions) are incorporated into rule generation/auditing—so untrusted third‑party content can directly influence actions.