git-workflow

Pass

Audited by Gen Agent Trust Hub on Jun 30, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill uses a placeholder for user-supplied input ($ARGUMENTS) that is interpolated directly into an instruction without boundary markers or sanitization.
  • Ingestion points: User-supplied input enters the context through the $ARGUMENTS variable in SKILL.md.
  • Boundary markers: No delimiters or explicit instructions to ignore embedded commands are present to separate the user data from the skill's instructions.
  • Capability inventory: The skill provides instructions for managing core git operations including branching, committing, rebasing, tagging, and pushing.
  • Sanitization: No input validation, filtering, or escaping is performed on the data provided in the $ARGUMENTS placeholder.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 30, 2026, 02:37 PM
Security Audit — agent-trust-hub — git-workflow