paperzilla

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

• Third-party content exposure detected (high risk: 0.75). The skill’s runtime workflow uses the pz CLI to fetch Paperzilla project feeds/papers/recommendations (e.g., pz feed ... / pz paper ... --markdown / pz rec ... --markdown), which are outsider-authored public/community content that can be ingested as readable text into the agent’s LLM context.