perplexity
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: 0.90). This skill explicitly uses Perplexity Search and Perplexity Ask to retrieve and synthesize content from public web pages, tutorials, blog posts, and URLs (open third‑party sites/WebSearch), so the agent will ingest untrusted third‑party content as part of its workflow.
Audit Metadata