product-discovery

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.80). The "Companion check" explicitly instructs the agent to run local filesystem commands and offer installing external skills via npx, which is functionality unrelated to product-discovery and could expose local state or install software — a hidden/out-of-scope behavior risk.

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

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow is triggered by user requests and then ingests that user-authored free-text prompt to generate JTBD/OST/assumption/experiment guidance.