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 query string (teamSearch(..., query, ...)), embeds it as messages: [{ role: "user", content: query }] and sends it to Perplexity via https://api.perplexity.ai/chat/completions, so outsider-authored free text can be ingested without selecting any specific item.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 26, 2026, 07:54 AM
Issues
1
Security Audit — snyk — perplexity-enterprise-rbac