perplexity
Warn
Audited by Snyk on Mar 30, 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 and tool descriptions (perplexity_ask, perplexity_research, perplexity_reason, and perplexity_search) explicitly perform web searches and return web-grounded answers, snippets, and citations via the OneKey Gateway/Perplexity APIs, so the agent ingests open/public web content that could contain untrusted, instruction-like text influencing its actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata