playdrop

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflow (SKILL.md and multiple references such as discovery.md, assets-and-generation.md, and live-ops.md) explicitly instructs the agent to fetch and inspect public Playdrop content using commands like "playdrop browse", "playdrop search", "playdrop detail", and "playdrop comments browse", which are user-generated/public platform assets and comments that the agent is expected to read and use to drive decisions and next actions.