x-twitter-automation

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to use Hermes Tweet's tweet_read/tweet_explore to search and read public X/Twitter tweets and replies (e.g., "Search tweets about...", "Use tweet_read for read-only endpoints such as tweet search..."), which are untrusted, user-generated third-party sources that the agent must read and analyze as part of its workflow.