use-git-agent

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill interacts with the host system by executing git-agent and git commands. This is the primary and intended function of the skill to manage repository state and perform automated commits.
  • [CREDENTIALS_SAFE]: The skill provides clear guidance on managing AI provider credentials. It encourages the use of local configuration files (~/.config/git-agent/config.yml) and explicitly demonstrates masking sensitive keys (sk-****) when displaying configuration via the git-agent config show command.
  • [INDIRECT_PROMPT_INJECTION]: The tool possesses an attack surface for indirect prompt injection as it ingests untrusted data from git diff and repository history to generate commit messages.
  • Ingestion points: Content is retrieved via git diff and git history analysis (git-agent init --scope).
  • Boundary markers: The documentation does not specify explicit delimiters used when passing this data to the underlying LLM.
  • Capability inventory: The skill can execute shell commands through the git-agent CLI and perform git operations.
  • Sanitization: No explicit sanitization or filtering of the repository content is mentioned in the CLI reference.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 01:28 PM