perplexity

Warn

Audited by Snyk on Mar 10, 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). The SKILL.md explicitly documents tools (perplexity_ask, perplexity_research, perplexity_reason, perplexity_search) that "search the web" and provide web-grounded answers or page snippets/citations (see the Tools section of SKILL.md), meaning the agent fetches and ingests open/public third-party web content which it reads and uses to generate actions/responses, enabling indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 10, 2026, 08:45 AM
Security Audit — snyk — perplexity