perplexity-policy-guardrails
Warn
Audited by Snyk on Aug 26, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The skill’s runtime path
policiedSearch(query, ...)ingests outsider-authored free text via thequeryparameter intosanitizeQueryand then directly sends it asmessages: [{ role: "user", content: clean }]to the Perplexity API.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata