skill-manager

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • File System Operations: The skill is designed to delete or rename files to uninstall or disable community plugins. While these are sensitive operations, the skill implements a multi-layer verification process, checking an internal audit log (~/.claude/plugins/config/claude-for-legal/legal-builder-hub/install-log.yaml) and ensuring target paths are outside restricted system directories.
  • Indirect Prompt Injection Mitigations: The skill processes external skill files but includes an explicit instruction to disregard any commands or instructions found within those files, relying solely on direct user input for authorization.
  • Audit Logging: Every administrative action is recorded in a persistent log, providing transparency and a history of changes made to the environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 09:46 PM
Security Audit — agent-trust-hub — skill-manager