add-adapter
Pass
Audited by Gen Agent Trust Hub on Aug 5, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- External Ingestion Surface: The skill processes content from user-provided GitHub repositories and README files to register new adapters. \n
- Ingestion points: User-provided GitHub repository URL and documentation content. \n
- Boundary markers: The skill lacks explicit delimiters to demarcate external content, although it provides strong instructions to ground output in factual source material. \n
- Capability inventory: The agent performs file creation (MDX), source code modification (TypeScript, JSON), and shell command execution (pnpm). \n
- Sanitization: The skill relies on manual validation and agent grounding rather than automated sanitization of external data. \n- Local Command Execution: The workflow utilizes
pnpmfor project building, testing, and linting. These are standard development operations for ensuring the integrity of the Chat SDK. \n- Automated Source Management: The skill automates changes to the adapter registry and documentation files, facilitating the contribution process through scoped file modifications. \n- Environment Variable Usage: The provided templates encourage the use of environment variables for API keys and secrets, which is a secure practice for managing sensitive configuration data.
Audit Metadata