langsmith-custom-apps

Pass

Audited by Gen Agent Trust Hub on Sep 20, 2026

Risk Level: SAFE
Full Analysis
  • Security Best Practices for Data Handling: The skill provides explicit instructions for developers to treat data retrieved from traces as untrusted. It recommends against using dangerouslySetInnerHTML and advises validating IDs and allowlisting values before they are used in filter strings or the UI, which helps prevent cross-site scripting (XSS) and injection vulnerabilities in the resulting applications.
  • Source Code Sanitization Guidance: A detailed checklist is included for developers to follow before sharing app source code externally. This includes steps to blank workspace identifiers, remove local configuration files, and verify that no credentials or private registry tokens are present in the build artifacts.
  • External Data Retrieval: The skill includes a Python snippet that fetches application source code from the official LangSmith API (api.smith.langchain.com) and writes it to the local file system. This functionality is intended to allow users to pull their application source when CLI support for that feature is missing in older versions.
  • Standard Development Workflow: The skill utilizes standard industry tools and commands, including npm install for dependency management and npx esbuild for local testing and verification. These are routine operations within a React/TypeScript development environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 20, 2026, 08:29 PM
Security Audit — agent-trust-hub — langsmith-custom-apps