skills/yaklang/yakit/commit-msg/Gen Agent Trust Hub

commit-msg

Pass

Audited by Gen Agent Trust Hub on Nov 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local git commands, including git add, git commit, git status, and git diff, to manage repository state. These operations are restricted to the local environment and the skill explicitly avoids pushing changes to remote servers.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from local file content and repository history to generate natural language summaries, creating a surface for indirect prompt injection.
  • Ingestion points: The skill reads output from git status --short, git diff --cached, git diff, and git log (SKILL.md).
  • Boundary markers: No specific delimiters or instructions to the model to ignore instructions embedded in the code diffs are defined.
  • Capability inventory: The skill possesses the ability to modify the local repository via git add -A and git commit (SKILL.md).
  • Sanitization: The skill mitigates risks through mandatory user confirmation checkpoints (Checkpoints in Step 1 and Step 4) and by using git commit -F with temporary files to prevent shell command injection through the commit message content.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 7, 2026, 08:59 PM