perplexity
Warn
Audited by Snyk on Jun 27, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). Perplexity Search/Ask at runtime can fetch and ingest public web page text (outsider-authored) into the agent’s LLM context as synthesized results/snippets, since the skill routes generic “search/find/look up/latest” requests to Perplexity tools.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata