cursor-skill-creator
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a meta-instruction set for the agent to help users create, organize, and format new skills specifically for the Cursor editor. It follows documented patterns for Cursor's internal skill system.
- [COMMAND_EXECUTION]: The skill instructs the agent to perform file system operations, specifically creating directories and markdown files within
.cursor/skills/(project-local) or~/.cursor/skills/(user-global). This is the intended and primary function of the skill and does not involve arbitrary command execution or shell injection. - [DATA_EXFILTRATION]: There are no network operations, hardcoded credentials, or instructions to access sensitive system files (such as SSH keys or environment variables) for external transmission.
- [PROMPT_INJECTION]: The skill does not contain instructions to override safety filters, bypass instructions, or reveal system prompts. It uses standard instructional language to guide the agent's behavior during the skill creation process.
- [INDIRECT_PROMPT_INJECTION]: Although the skill creates new instructions (skills) that will be processed by the agent later, it does not ingest data from untrusted external sources like URLs or APIs, which significantly limits the surface for indirect injection attacks.
Audit Metadata