social-content
Warn
Audited by Snyk on Mar 4, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill's reverse-engineering workflow (references/reverse-engineering.md, "SCRAPE" step) explicitly instructs collecting/scraping 500–1000+ public posts from LinkedIn, Twitter/X and other creators using tools like Apify/PhantomBuster, which requires ingesting untrusted, user-generated third-party content that the agent is expected to analyze and use to drive subsequent actions.
Audit Metadata