linkedin-post-research

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

• Third-party content exposure detected (high risk: 0.80). The skill's script and SKILL.md explicitly call the Crustdata API (/screener/linkedin_posts/keyword_search) to fetch LinkedIn posts (user-generated, public social-media content) and the code parses and acts on post text/metadata (post_preview, sorting/filtering and downstream chaining), so untrusted third-party content is ingested and can influence subsequent actions.