design

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md explicitly instructs the agent to fetch and read external repository URLs and arbitrary reference URLs ("When the user provides a repository URL or pastes source code... read the actual source" and "When only a URL is provided: fetching it returns extracted text only" / brand preset flow), meaning it ingests untrusted, user-provided third‑party content and uses those contents to drive design decisions and code generation.