init-project

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill automates the creation of a local research project environment. It uses standard filesystem and version control utilities such as mkdir, ln, and git to set up the workspace as described in its documentation.- [COMMAND_EXECUTION]: The skill utilizes shell commands to scaffold directories and create symbolic links for document synchronization. These actions are performed using restricted tool definitions and are driven by user input provided during the interactive setup phase.- [INDIRECT_PROMPT_INJECTION]: The skill captures user-supplied metadata, such as research questions and project titles, and persists them into project instruction files like CLAUDE.md. While this data influences the behavior of future agent sessions in that directory, this behavior is the primary intended function of the project bootstrapping process.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 06:16 AM
Security Audit — agent-trust-hub — init-project