content-pattern-analyzer-sms

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflow (SKILL.md "Path A — With BlackTwist") instructs the agent to call BlackTwist methods like list_posts and get_post_analytics to retrieve full social‑media post history (user-generated, public third‑party content) and then read/interpret that content to drive pattern-based recommendations, exposing the agent to untrusted third‑party content that can influence actions.