instagram-hashtag-posts

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

• Third-party content exposure detected (high risk: 0.85). The skill navigates to Instagram’s hashtag search page and then runs eval "$(python scripts/fetch-hashtag-posts.py '{hashtag}')" which executes browser JS that POSTs to Instagram’s GraphQL endpoint and ingests the returned JSON (outsider-authored public web content fetched at runtime) into the agent’s context via the tool output.