bug-class-audit

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

• Third-party content exposure detected (high risk: 0.85). The required workflow delegates to a subagent that runs gh pr view <num> / gh pr diff <num> and classifies PR descriptions/diffs, which are outsider-authored free text (PR authors other than the operating user) that can include prompt-injection content into the LLM context.