ln-011-agent-installer

Pass

Audited by Gen Agent Trust Hub on Apr 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill manages the installation of official, well-known packages (@openai/codex and @anthropic-ai/claude-code) from the standard NPM registry.
  • [SAFE]: Shell command execution is restricted to standard package manager operations and health checks.
  • [SAFE]: File system access is limited to the specific configuration files of the agents being managed and the generation of a summary artifact.
  • [SAFE]: The skill documentation includes explicit warnings against using sudo for installations, recommending secure local alternatives.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 26, 2026, 01:34 PM