google-videos-search

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

• Third-party content exposure detected (high risk: 0.75). The required workflow calls an external Frevana endpoint and then reads the returned HTTP response body as text (scripts/search_google_videos.sh:148-168) and prints it to stdout, so any free-form content in that outsider response can be ingested into the agent’s LLM context.