skills/spm1001/trousse/ardoise/Gen Agent Trust Hub

ardoise

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill dynamically locates and executes a local shell script (ardoise.sh) found within the plugin cache directory to initialize the isolated environment. This script is used to strip environment variables and reconfigure the home directory for context isolation.
  • [EXTERNAL_DOWNLOADS]: The documentation references external tools and repositories, specifically pointing to the official GitHub repository for Apple's containerization tool (github.com/apple/container). It also lists standard package registries (NPM) for installing the agent's core CLI.
  • [REMOTE_CODE_EXECUTION]: The reference documentation for Apple Containers includes a Dockerfile template that utilizes remote script execution patterns (curl | bash) to install system dependencies. These patterns are directed at well-known and reputable technology providers, such as NodeSource for Node.js and Astral for the uv package manager.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 08:46 AM
Security Audit — agent-trust-hub — ardoise