agent-builder

Warn

Audited by Snyk on Feb 18, 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 documents and recommends using web-facing MCP tools (e.g., WebSearch, WebFetch, Exa Search, Perplexity and related mcp__exasearch__/mcp__perplexity-ask__* entries) and the "Research Agent" pattern which instructs the agent to fetch and load web/public documentation, so the agent would read untrusted third-party web content as part of its workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 18, 2026, 12:01 AM