skills/lvlup-sw/exarchos/prune/Gen Agent Trust Hub

prune

Pass

Audited by Gen Agent Trust Hub on Jul 7, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides a structured and interactive process for workflow maintenance. It utilizes a dry-run mechanism to show users the impact of actions before execution, which is a key security and operational best practice.\n- [COMMAND_EXECUTION]: The skill mentions the use of git and gh (GitHub CLI) by the underlying MCP server to perform safeguard checks (e.g., checking for open pull requests or recent commits). These are standard tools used within their intended scope of version control management.\n- [PROMPT_INJECTION]: No prompt injection or behavior override patterns were detected. The instructions are descriptive of the tool's functionality.\n- [DATA_EXFILTRATION]: No evidence of unauthorized data access or exfiltration was found. Operations are limited to the Exarchos state directory and standard VCS metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 7, 2026, 06:24 PM
Security Audit — agent-trust-hub — prune