langchain
Warn
Audited by Snyk on Mar 7, 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.md includes an "Agent for Web Search" example that loads the serpapi web-search tool and runs queries (agent.run("Search for latest AI news")), meaning the agent fetches and ingests open web results (untrusted third‑party content) which it reads and can use to drive subsequent actions.
Audit Metadata