instagram-profile

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

• Third-party content exposure detected (high risk: 0.70). The required workflow calls Frevana’s /service/instagram-profile endpoint and then reads the returned HTTP response body as text (raw = ...read_text(...)) and prints it to stdout (cat "$RESULT_FILE"), so any outsider-authored free text contained in that API response is ingested into the agent’s LLM context via the tool output.