mediatoolkit

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

• Third-party content exposure detected (high risk: 0.80). The skill’s workflow instructs the agent to fetch data from the Mediatoolkit service (see "Proxy requests" and the "Running actions"/"Popular actions" sections) which returns mentions from online news and social media (untrusted, user-generated third‑party content) that the agent is expected to read/interpret and could materially influence its actions.