langsmith-trace

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

• Third-party content exposure detected (medium risk: 0.30). The agent queries LangSmith traces and run data using the langsmith CLI tool, which can ingest arbitrary user-submitted input and trace logs containing untrusted third-party free text.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill references an installation script on GitHub (https://raw.githubusercontent.com/langchain-ai/langsmith-cli/main/scripts/install.sh) which constitutes an operational dependency.