x-tweet-search

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches raw, user-generated tweets from the public X API (see SKILL.md and scripts/search.sh which call https://api.x.com/2/tweets/search/recent) and returns that untrusted third‑party content for the agent to read and act on, so third‑party instructions could influence behavior.