ln-011-agent-installer
Pass
Audited by Gen Agent Trust Hub on May 12, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill executes command-line operations to install and verify software. Specifically, it uses
npm install -gto manage official packages from OpenAI and Anthropic. These operations are restricted to hardcoded, well-known package names. - [EXTERNAL_DOWNLOADS]: The skill fetches the official
@openai/codexand@anthropic-ai/claude-codepackages from the public npm registry. These are verified tools provided by established technology organizations. - [SAFE]: The skill incorporates a sanity check that reads local configuration files (
~/.codex/config.toml) to detect configuration drift. This is a read-only diagnostic step with no evidence of data exfiltration or unauthorized network communication.
Audit Metadata