Skills
skills/richfrem/agent-plugins-skills/os-clean-locks/Gen Agent Trust Hub

os-clean-locks

Pass

Audited by Gen Agent Trust Hub on Apr 3, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool to perform system-level maintenance, including listing and deleting files within the context/.locks/ directory. It also invokes a local Python script (context/kernel.py) to emit events and update the internal state of the Agentic OS.
  • [SAFE]: All identified operations are restricted to the local file system and intended for internal state management. No evidence of data exfiltration, remote code execution, obfuscation, or unauthorized privilege escalation was found in the skill's instructions or scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 3, 2026, 06:08 PM