perplexity-enterprise-rbac
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). In SKILL.md’s workflow, the agent takes a runtime user-supplied
querystring (teamSearch(..., query, ...)), embeds it asmessages: [{ role: "user", content: query }]and sends it to Perplexity viahttps://api.perplexity.ai/chat/completions, so outsider-authored free text can be ingested without selecting any specific item.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata