tweetsmash-api

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

• Third-party content exposure detected (high risk: 0.85). The required workflow calls TweetSmash API endpoints (e.g., GET /bookmarks) and then feeds the returned JSON fields like tweet_details.text into the agent’s response/context; this is outsider-authored content because it is user-generated tweet text retrieved at runtime from an external service, not authored by the operating user.