git-spice

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill is primarily composed of command-line instructions for git-spice, git, glab, and gh. These commands are used for their intended purposes: repository initialization, branch management, and merge request updates.
  • [EXTERNAL_DOWNLOADS]: The configuration in prek.toml references standard development tools such as typos and lychee for linting and link checking. These are well-known utilities and pose no security risk.
  • [DATA_EXPOSURE]: The skill provides instructions for authenticating with GitLab using git-spice auth login, which is a standard procedure for the tool. It does not involve hardcoded secrets or unauthorized exfiltration of sensitive data.
  • [INDIRECT_PROMPT_INJECTION]: The skill involves the agent generating merge request descriptions and commit messages. While this creates a surface for indirect prompt injection if the agent processes untrusted external data (like a PR body) without sanitization, the skill itself provides structured templates that help mitigate accidental misinterpretation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 10:02 AM