wiki

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow explicitly instructs the agent to fetch and read an arbitrary repository (e.g., "Read a repository", "Open and read the actual source files", and the CLI example using --repo-url in SKILL.md), which means it ingests untrusted, user-provided public repo content and uses that content to drive planning, sub-agent delegation, and page-generation decisions.