outlier-post-finder

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

• Third-party content exposure detected (high risk: 0.85). Outsider-authored free text is ingested when the skill fetches public posts from external platforms (e.g., via ScrapeCreators feed/detail endpoints) and then enriches them with captions/transcripts/comments, which are readable text authored by other users/creators and become part of the agent’s LLM context for analysis and quoting.