exa-x-search

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs calling mcporter's exa-search.web_search_advanced_exa with category=tweet to fetch public X/Twitter tweets (user-generated, untrusted content) which the agent ingests and uses to produce results and action-driving notes, so third-party content could inject instructions indirectly.