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). SKILL.md's "Reverse Engineering Viral Content" (step 2, "SCRAPE — Collect Posts at Scale") explicitly instructs scraping/publicly collecting posts from social platforms like LinkedIn and Twitter using tools such as Apify and PhantomBuster, so the agent would ingest untrusted user-generated content that could influence analysis and subsequent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 4, 2026, 01:57 PM