perplexity
Warn
Audited by Snyk on Apr 6, 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 directs the agent to call Perplexity APIs (e.g., https://api.perplexity.ai/chat/completions and /search) to perform web searches and return synthesized answers with citations and search_result snippets from arbitrary public domains, meaning the agent ingests and acts on untrusted third‑party web content.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata