NYC

influencer-analyzer

Warn

Audited by Snyk on Feb 15, 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 explicitly instructs the agent to use Perplexity/DuckDuckGo to find and scrape public influencer content (Twitter, YouTube, Substack) and includes web‑scraping dependencies (requests, beautifulsoup4), so it fetches and analyzes untrusted user‑generated third‑party content as part of its workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 09:40 PM