setup-agentic-repository

Pass

Audited by Gen Agent Trust Hub on Sep 22, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes a local bash script (scripts/scaffold.sh) to automate the creation of the documentation directory structure and the placement of template files. The script uses standard utilities like mkdir, sed, grep, and printf for idempotent file operations and basic string substitution. It includes safety checks to prevent directory traversal and does not require elevated privileges.
  • [INDIRECT_PROMPT_INJECTION]: As part of its discovery phase, the skill reads repository metadata and configuration files (e.g., package.json, README.md, .git/config) to identify the tech stack and project conventions. While reading untrusted repository content is a prerequisite for its function, the skill follows a structured process using predefined templates and requires user confirmation of its findings before generating any files, which minimizes the risk of malicious repository content subverting the agent's behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 22, 2026, 01:59 PM