perplexity
Warn
Audited by Snyk on Feb 16, 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 performs real-time web searches via Perplexity and returns AI responses containing web-search results/citations (open web content) in the workflow result messages (.payload.messages[] → .content), so the agent will read and interpret untrusted third‑party content.
Audit Metadata