task-routing

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

• Third-party content exposure detected (high risk: 0.80). The skill's workflow explicitly instructs the agent to run public content-browsing commands (e.g., "use playdrop documentation browse and playdrop documentation read <path>" in SKILL.md and "playdrop browse ...", "playdrop search " in references/discovery.md) to inspect published apps, assets, demos and documentation, which are untrusted/user-generated public sources that the agent is expected to read and that can materially change routing and follow-up actions.