pm-okr-metric-validity-audit

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

• Third-party content exposure detected (high risk: 0.70). The skill’s runtime behavior is to audit OKRs/KPIs “present in work being reviewed or generated,” which implies it ingests outsider-authored OKR/metric text from other parties (e.g., other users/teams) into the LLM context for evaluation; the SKILL.md does not restrict inputs to user-authored content only.