influencer-discovery

Warn

Audited by Snyk on Mar 2, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). The SKILL.md workflow (Steps 3–7) explicitly directs the agent to search and ingest content from public third-party sources — e.g., YouTube, X/Twitter, blogs, Substack/newsletters, Apple Podcasts/Spotify, Instagram/Facebook, and conference speaker pages — and to use that discovered content to score, rank, and decide outreach priorities, which meets all criteria for potential indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 2, 2026, 10:01 PM