pm-prioritize

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

• Third-party content exposure detected (medium risk: 0.65). The skill can fetch outsider-authored free text from public GitHub issues via the runtime gh issue list ... --json number,title,body path (or other backlog sources like cat $TASKS_FILE if that file contains non-user-authored content), and then feeds the issue body/pasted requirement descriptions into the LLM for scoring.