ai-provider-cohere-sdk
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a high-quality integration guide for the official
cohere-ailibrary, focusing on V2 API patterns. - [CREDENTIALS_SAFE]: The documentation includes explicit warnings and 'red flags' against hardcoding API keys, demonstrating the correct use of
process.envfor sensitive tokens. - [COMMAND_EXECUTION]: All examples are standard TypeScript/JavaScript code for interacting with API endpoints; no suspicious shell commands or unauthorized file system operations were identified.
- [INDIRECT_PROMPT_INJECTION]: While the skill describes RAG and tool-use patterns which are common surfaces for indirect injection, it provides the necessary structure (citations, tool roles) to manage these interactions according to SDK specifications.
Audit Metadata