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
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata