perplexity-web-research

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 uses the llm CLI with the Perplexity plugin and Perplexity API (e.g., sonar/sonar-pro models with "Web Search" enabled) to perform live searches and synthesize real-time public web content, so the agent will fetch and read untrusted third‑party webpages and user-generated sources.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:59 AM