social-content
Warn
Audited by Snyk on Jun 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The skill’s runtime workflow includes “Reverse Engineering Viral Content” where it instructs collecting and analyzing posts from “top creators” (via tools like Apify/Phantom Buster or manual copy/paste), meaning outsider-authored post text is ingested into the agent’s LLM context for pattern extraction.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata