scienceclaw-verification

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

• Third-party content exposure detected (high risk: 0.90). The skill's Stage 2 "Evidence Search" explicitly directs the agent to use the scienceclaw-retrieval tool to locate papers and seek independent corroboration from external sources, so the agent will fetch and read open/public third-party content (papers/web sources) that can materially influence verification decisions.