skills/skrrt-sh/claude-plugins/commit/Gen Agent Trust Hub

commit

Pass

Audited by Gen Agent Trust Hub on Apr 5, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted content from the repository code and diffs.\n
  • Ingestion points: Repository diffs and status information are read using git diff and git status (SKILL.md).\n
  • Boundary markers: No explicit delimiters or isolation instructions are provided to separate the diff content from agent instructions.\n
  • Capability inventory: The skill has the capability to modify repository state using git add and git commit (SKILL.md).\n
  • Sanitization: No sanitization or validation is applied to the ingested diff content before it is used to generate commit headers and bodies.\n- [COMMAND_EXECUTION]: The skill uses a restricted subset of local git commands to perform its duties.\n
  • Evidence: Use of git status, git diff, git add, and git commit (SKILL.md).\n
  • Context: The skill instructions emphasize staying within a safe subset of commands and treat staging and committing as actions requiring human-approval or human-in-the-loop oversight.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 5, 2026, 09:42 AM