cursor-agent
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for constructing and executing
cursor-agentcommands with various options. These include interactions for planning, task execution, and session management. - [EXTERNAL_DOWNLOADS]: Contains instructions for installing the CLI via a remote script (
curl https://cursor.com/install | bash). Per safety guidelines for well-known services (Cursor), this is documented but does not escalate the verdict. - [PRIVILEGE_ESCALATION]: The skill mentions
--trust,--yolo, and--sandbox disabledflags but explicitly forbids using them without specific, named user authorization, ensuring the agent follows a least-privilege model. - [DATA_EXPOSURE]: Includes logic to redact secrets and tokens from CLI output and explicitly forbids printing API keys or account dumps.
Audit Metadata