researching-web

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: 0.90). This skill calls Perplexity AI web search (mcp__perplexity-ask__perplexity_ask) to fetch and ingest open/public web content—including user-generated sites and forums—that the agent reads as part of its workflow, enabling possible indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 09:07 PM