langsmith-trace

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

• Third-party content exposure detected (medium risk: 0.30). The agent skill queries and reads trace data from LangSmith via CLI commands, which may contain user inputs, prompts, and outputs from third-party end users processed by the monitored application.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs downloading and executing a remote installation script from raw.githubusercontent.com for the LangChain CLI tool, which constitutes a weak/unknown/suspicious operational external dependency.