alterlab-pra-social-content

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflow and Agentic Protocol explicitly require the agent to "search the web" for trending formats, platform algorithm updates, hashtag performance, and competitor social content strategies (SKILL.md "Workflow" and "Agentic Protocol"), meaning it will fetch and read open/public social media and web content and use those findings to drive decisions and deliverables, which could enable indirect prompt injection.