cursor-composer-workflows
Pass
Audited by Gen Agent Trust Hub on Apr 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of markdown documentation and instructional examples for using Cursor Composer's multi-file editing and code generation features.
- [SAFE]: No executable scripts, automated terminal commands, or remote code downloads are present within the skill files. All instructions are aimed at human-in-the-loop workflows where the user provides prompts to an AI agent.
- [SAFE]: All external links point to legitimate documentation for the Cursor IDE (docs.cursor.com) or the author's professional websites (intentsolutions.io, jeremylongshore.com). These links are clearly labeled and serve as resource references.
- [SAFE]: The skill's metadata specifies allowed-tools including Bash(cmd:*), which is a platform-level configuration that scopes the agent's capabilities rather than an active security finding within the skill's content.
- [SAFE]: No evidence of prompt injection, data exfiltration patterns, or persistence mechanisms was detected in any of the provided files.
Audit Metadata