research

Warn

Audited by Snyk on Feb 16, 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 explicitly launches web research agents (perplexity-researcher, claude-researcher, gemini-researcher) that perform Perplexity API / web searches and references Brightdata scraping tools (mcp__Brightdata__scrape_as_markdown, search_engine) to fetch arbitrary public webpages and URLs, so the agent will ingest untrusted, user/public third‑party content as part of its workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:09 AM