langgraph

Warn

Audited by Snyk on Feb 19, 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's "Basic Agent Graph" defines a search tool with the docstring "Search the web for information" and includes that tool in the agent's toolset (tools bound to the LLM and used in the agent/tool loop), which clearly indicates the agent will fetch and ingest open web (third‑party) results that can influence its subsequent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 19, 2026, 04:11 AM