gemini-companion

Pass

Audited by Gen Agent Trust Hub on Apr 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues detected. No malicious patterns, obfuscation, or persistence mechanisms were found.- [COMMAND_EXECUTION]: Shell execution is restricted to the gemini command line interface via the allowed-tools frontmatter, which acts as a security control to prevent arbitrary command execution.- [DATA_EXFILTRATION]: The skill does not contain any code or instructions to transmit data to external servers. It relies on local CLI tools and the Read tool for processing local files.- [PROMPT_INJECTION]: Instructions provide clear operational guidelines for the AI agent without attempting to override safety protocols or baseline behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 19, 2026, 02:48 PM