git-submodule

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill instructions facilitate the integration of external Git repositories via submodules. This creates a surface for indirect prompt injection, as the agent may subsequently process untrusted data (such as documentation or README files) contained within those external repositories.
  • Ingestion points: Content from external Git repositories added or updated via git submodule commands.
  • Boundary markers: None identified in the provided instructions; the agent is not instructed to treat imported content as untrusted.
  • Capability inventory: The skill utilizes git commands to manage repository state and file system contents.
  • Sanitization: No sanitization or validation steps are included for the content of external submodules.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 06:59 AM
Security Audit — agent-trust-hub — git-submodule