perplexity

Warn

Audited by Snyk on Mar 17, 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 explicitly performs real-time web search and URL fetching (see SKILL.md and docs/perplexity_api_reference.md describing the Search API, Agent API tools web_search/fetch_url and Sonar "web-grounded" responses) and the runtime code (perplexity.py) calls the Perplexity chat/completions endpoint to synthesize answers with citations, so public third-party webpages are fetched and directly influence the agent's outputs.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 17, 2026, 06:38 AM
Issues
1
Security Audit — snyk — perplexity