typst-writer

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to fetch and search public web sources (e.g., Typst Universe pages, GitHub repos such as https://github.com/typst/packages via gh or SearxNG search, and even says "Use WebFetch" to retrieve documentation), which are untrusted, user-generated third-party content that the agent is expected to read and interpret as part of its workflow.