product-capability

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

• Third-party content exposure detected (medium risk: 0.65). The skill’s runtime workflow explicitly ingests “Product intent” from an issue/discussion/PRD/founder message and “Current architecture” from repo docs, meaning it can read outsider-authored free text (e.g., issue/discussion body written by someone other than the operating user) into the agent’s LLM context via those inputs.