lov-git-commit-with-context

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from git status outputs and diffs to generate commit messages. The workflow in SKILL.md mandates a manual confirmation step where the user reviews staged hunks and the generated message before the commit is finalized, effectively mitigating risks from malicious instructions embedded in the codebase.
  • [COMMAND_EXECUTION]: The skill performs Git operations such as staging and committing changes. The instructions in SKILL.md explicitly require that project-specific hooks are executed and that safety-skipping parameters (such as --no-verify) are not used, maintaining the security integrity of the local development environment.
  • [DYNAMIC_EXECUTION]: The provided validation utility scripts/validate_skill.py uses yaml.safe_load() to process YAML content. This is a secure implementation that prevents arbitrary code execution during the parsing of skill metadata and configuration files.
  • [DATA_EXPOSURE]: The scripts/profile_store.py script manages local identity and preference data. It includes a security filter (SENSITIVE_PARTS) designed to identify and block the storage of credentials such as tokens, secrets, passwords, and API keys within the shared user profile.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 09:47 AM
Security Audit — agent-trust-hub — lov-git-commit-with-context