gemini-command-development
Pass
Audited by Gen Agent Trust Hub on Mar 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were detected. The skill provides instructions and examples for TOML-based command configuration. It appropriately requests file system tools ('Read', 'Glob', 'Grep') for workspace interaction.
- [PROMPT_INJECTION]: The skill includes strong behavioral directives (e.g., 'MANDATORY', 'STOP') to ensure the agent consults the 'gemini-cli-docs' skill before answering. While these are forceful instructions, they serve as operational constraints for accuracy and do not attempt to bypass safety filters or exfiltrate data.
Audit Metadata