skills/segodnya/agents/dev-feedback/Gen Agent Trust Hub

dev-feedback

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses subprocess.run within its Python scripts (fetch_mrs.py and fetch_mr_details.py) to invoke the official glab CLI for interacting with GitLab APIs. The arguments (username, project ID, MR IID, hostname) are passed as a list to the subprocess, which mitigates standard shell injection risks. The skill explicitly requires the user to grant permissions for these scripts in the environment configuration.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 12:31 PM
Security Audit — agent-trust-hub — dev-feedback