Skills
Navigate
skills/stuartf303/vandaemon/speckit-git-commit/Gen Agent Trust Hub

speckit-git-commit

Pass

Audited by Gen Agent Trust Hub on Oct 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute local scripts located at .specify/extensions/git/scripts/bash/auto-commit.sh or .specify/extensions/git/scripts/powershell/auto-commit.ps1. These scripts are used to perform git add . and git commit operations as part of the intended automation workflow.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data from a configuration file, which presents an attack surface for indirect instructions.
  • Ingestion points: Reads parameters such as enabled status and commit message from .specify/extensions/git/git-config.yml.
  • Boundary markers: The instructions do not define delimiters or warnings to ignore potentially malicious content within the configuration file.
  • Capability inventory: The skill can execute local shell/PowerShell scripts and invoke Git commands via the agent's environment.
  • Sanitization: There is no mention of validation or escaping for the message string or the <event_name> argument before they are processed or passed to the scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 23, 2026, 07:57 PM