cursor-sdk

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a technical reference for the @cursor/sdk TypeScript library. It provides legitimate implementation patterns for agent creation, error handling, and runtime configuration without introducing malicious instructions.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The documentation correctly advises using process.env.CURSOR_API_KEY for authentication. This follows industry-standard security practices for credential management and avoids the risk of hardcoded secrets.
  • [INDIRECT_PROMPT_INJECTION]: The skill documents an interface for agents to process repository content and user-supplied prompts. While this creates a surface for indirect prompt injection at the application level, the skill itself does not contain malicious payloads and provides structural patterns to handle these interactions safely.
  • [COMMAND_EXECUTION]: The code examples provided demonstrate legitimate use of the Cursor SDK to perform automated coding tasks. The operations are scoped to the developer's local environment or explicit cloud repositories as per the user's intent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 11:52 AM
Security Audit — agent-trust-hub — cursor-sdk