google-short-videos-search

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

• Third-party content exposure detected (medium risk: 0.65). The required workflow calls Frevana’s /service/google-short-videos endpoint and then reads the returned HTTP response body as text (via python3 reading RESPONSE_FILE and printing/writing it), so any outsider-authored free text contained in that response can be passed into the agent’s LLM context through the skill’s stdout.