agent-skills-manager

Pass

Audited by Gen Agent Trust Hub on Oct 17, 2026

Risk Level: SAFEREMOTE_CODE_EXECUTIONPERSISTENCECOMMAND_EXECUTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill includes a bootstrap command that downloads and executes a shell script directly from the vendor's GitHub repository.
  • Evidence: The installation instructions utilize curl -fsSL https://raw.githubusercontent.com/ravnhq/ai-toolkit/main/install.sh | bash to set up the corvus tool.
  • [PERSISTENCE]: The skill provides instructions to modify and source shell configuration files, ensuring the CLI tool and its completions are persistently available across terminal sessions.
  • Evidence: Guidance to source ~/.zshrc or ~/.bashrc and instructions for creating fish shell completion files in ~/.config/fish/completions/.
  • [COMMAND_EXECUTION]: The core functionality of the skill involves executing the corvus CLI to perform file system operations, such as installing skills into project-specific directories or global configuration paths.
  • Evidence: Documentation of commands like corvus install, corvus sync, and corvus remove for managing skill distribution and configuration files.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 17, 2026, 03:00 AM