git-commit-rewrite

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses destructive git commands such as git filter-branch and git push --force. While intended for history rewriting, these commands can permanently alter or delete data if misused or if the 'force mode' is accidentally triggered. \n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from git commit history. \n
  • Ingestion points: Git commit subjects and bodies are read from the repository history via git log. \n
  • Boundary markers: The skill lacks explicit boundary markers or instructions to ignore embedded commands within the commit messages being processed. \n
  • Capability inventory: The skill has the ability to execute shell commands (git filter-branch, git push --force) and modify repository history. \n
  • Sanitization: While it uses regex for commit formatting, it does not sanitize the content against prompt injection. A malicious commit message containing the word 'force' could potentially trigger the skill's 'Force mode', causing the agent to skip safety checks and user confirmation for destructive actions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 04:14 PM