langgraph-docs

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill instructs the agent to fetch and read public documentation from https://docs.langchain.com/llms.txt and then to retrieve selected documentation URLs from that index, which exposes the agent to untrusted, third-party web content that it will read and interpret.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly directs the agent at runtime to fetch and use the content of https://docs.langchain.com/llms.txt (and then selected documentation URLs) to directly control its prompts/instructions, making that external content a required runtime dependency.