viral-post-writer

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflow explicitly instructs the agent to run web_search and web_browse (e.g., "use web_search \"[product name] features pricing\"", Step 2 research, and Step 2.5 searches like web_search \"[product name] review site:linkedin.com\" and site:x.com), meaning it ingests untrusted public social/media and review content and uses those findings to choose frameworks and drive post-writing decisions, which could enable indirect prompt injection.