speckit-git-feature

Pass

Audited by Gen Agent Trust Hub on Aug 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local scripts located at .specify/extensions/git/scripts/bash/create-new-feature.sh and .specify/extensions/git/scripts/powershell/create-new-feature.ps1. These executions are essential for the skill's functionality to manage Git branches within the spec-kit environment.- [PROMPT_INJECTION]: The skill processes untrusted user data from $ARGUMENTS and feature descriptions, which are interpolated into shell command lines. This creates an indirect prompt injection surface where malicious input could attempt to manipulate the command's behavior.
  • Ingestion points: User input from the $ARGUMENTS block and the feature description provided in the request.
  • Boundary markers: None; input is wrapped in double quotes in the command template but no escaping or sanitization is performed.
  • Capability inventory: Execution of shell and PowerShell scripts using project-local paths.
  • Sanitization: No input validation or sanitization is specified before parameters are passed to the underlying scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 7, 2026, 06:22 AM
Security Audit — agent-trust-hub — speckit-git-feature