perplexity-reliability-patterns
Warn
Audited by Snyk on Mar 11, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). Because the skill explicitly uses Perplexity Sonar to perform live web searches (SKILL.md Overview) and streams responses with citations that the code then validates by fetching cited URLs (validate_citations), 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