flix

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly requires the agent to fetch and read public web documentation (e.g., https://api.flix.dev/ and pages under https://doc.flix.dev/ such as /interoperability.html) before writing code, so the agent will ingest and act on third‑party web content as part of its workflow.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly mandates fetching external documentation at runtime (e.g., the Flix stdlib and docs such as https://api.flix.dev/ and https://doc.flix.dev/interoperability.html) and relies on that fetched content as a required context that directly controls the agent's instructions for generating code, so these runtime fetches meet the criteria for risk.