perplexity

Warn

Audited by Snyk on Feb 17, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). This skill uses the Perplexity API to search the open web (via the search scripts in scripts/search.mjs), ingesting and returning content from public websites and user-generated sources that the agent reads and interprets as part of its responses.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 01:50 PM