instagram-profile-posts

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

• Third-party content exposure detected (high risk: 0.85). The required workflow runs browser-act/fetch at runtime against Instagram API endpoints and ingests the returned JSON fields (e.g., caption.text, location.name) into the agent context; these are free-form text authored by the Instagram account owner (an outsider relative to the operating user), which is then passed through the tool outputs into the LLM context.