x-api

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

• Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md explicitly reads public, user-generated X/Twitter content (e.g., "Check mentions", "search recent tweets", and tweet lookups via the Twitter API endpoints shown) and the agent is expected to fetch and act on that content (mentions/tweets) as part of its workflow, allowing untrusted third-party text to influence actions.