safe-change
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions focus on legitimate software engineering best practices, such as performing impact checks before modifying shared symbols and ensuring backward compatibility.
- [SAFE]: No evidence of prompt injection, data exfiltration, or unauthorized command execution was found. All file operations are restricted to the local workspace and the project's internal wiki/logging system (
llmwiki/). - [SAFE]: The skill relies on other internal skills (e.g.,
impact-check,verify-before-commit) which is a standard pattern for modular AI agent workflows. - [SAFE]: All external references (such as the wiki draft structure) are consistent with the stated purpose of maintaining a development log.
Audit Metadata