here-be-git

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands to initialize a git repository (git init) and commit configuration files (git commit) to the local version control system.
  • [INDIRECT_PROMPT_INJECTION]: The skill establishes a surface for indirect prompt injection by creating a configuration file (AGENTS.md) designed to direct future AI agent behavior using high-priority, imperative language.
  • Ingestion points: Accepts user-provided text for .gitignore patterns and writes a static block of behavioral instructions into the AGENTS.md file.
  • Boundary markers: There are no explicit markers or safety instructions surrounding the user-provided content or the injected agent instructions within the generated files.
  • Capability inventory: The skill possesses the capability to write to the local file system (AGENTS.md, .gitignore) and execute shell commands (git).
  • Sanitization: No validation or escaping of user-provided patterns is performed before writing them to the .gitignore file.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 06:04 PM
Security Audit — agent-trust-hub — here-be-git