skills/derogab/agent-kit/commit/Gen Agent Trust Hub

commit

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEDYNAMIC_CONTEXT_INJECTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DYNAMIC_CONTEXT_INJECTION]: The skill employs ! prefixed backtick commands (e.g., git diff --staged, git branch --show-current, git log --oneline -5) which execute automatically at load time to populate the agent's context.
  • [COMMAND_EXECUTION]: Local shell commands are invoked to read repository state, staged changes, and history.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input in the form of git diffs and commit messages from the repository, which provides a surface for indirect prompt injection if the repository contains malicious content.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 08:04 AM