langchain-architecture

Warn

Audited by Snyk on Feb 28, 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 Quick Start example explicitly loads the "serpapi" tool (load_tools(["serpapi", ...])) and the doc states the skill is for "integrating LLMs with external data sources and APIs," meaning the agent is expected to fetch and interpret public web/search results (untrusted third‑party content) that can influence its actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 28, 2026, 09:04 AM