x-api

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

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime flow calls X API endpoints like https://api.x.com/2/tweets/search/recent and .../users/{user_id}/tweets, which return tweet body text authored by other users (outsider-authored free text) that the agent would ingest via resp.json() into the LLM context.