langchain-architecture
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: 0.90). The skill's SKILL.md examples and workflow (e.g., Quick Start's load_tools(["serpapi", ...]) and references to "Self-Ask with Search" / RetrievalQA) explicitly show the agent fetching and ingesting open web/search results and public documents, which are untrusted third-party content that can influence tool selection and agent actions.
Audit Metadata