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