pplx-sdk-dev
Warn
Audited by Snyk on Feb 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill's "reverse-engineer" and "spa-expert" workflows explicitly capture and analyze cURL/network traffic and SPA runtime state from external websites (e.g., "perplexity.ai DevTools" and via CDP/Chrome extension), so the agent will ingest and interpret untrusted third-party web content.
Audit Metadata