research-ideation

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

• Third-party content exposure detected (high risk: 0.75). The skill’s default runtime path calls superpower-writing:literature-review and superpower-writing:research-lookup during Phase 1, which can fetch and ingest outsider-authored web content (public pages/papers) into the agent’s LLM context for synthesis and gap-finding.