social-listening

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

• Third-party content exposure detected (high risk: 0.95). The required workflow step “Collect posts/comments into one list (… text …)” (SKILL.md:20) implies the agent ingests outsider-authored free-form social media content from multiple public platforms via runtime search endpoints (SKILL.md:15-18), which is then used for sentiment/theme analysis and quoted in the digest (SKILL.md:21-24).