langgraph

Warn

Audited by Snyk on Mar 10, 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.md "Basic Agent Graph" pattern defines a tool named search with the docstring "Search the web for information" and wires tools into the agent (ToolNode and llm.bind_tools), so the agent is expected to execute web/search tools that ingest untrusted public web content and then use those results to drive routing and actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 10, 2026, 06:50 AM