lwy-project-rules-writer
Pass
Audited by Gen Agent Trust Hub on Jun 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were detected in the skill's instructions or supporting scripts.
- [COMMAND_EXECUTION]: The skill executes a local bundled JavaScript file (
scripts/cli.cjs) to initialize rule files. The script performs standard file operations (reading templates and writing rendered output) based on project analysis and user input. - [DATA_EXFILTRATION]: No exfiltration patterns found. Project metadata (structure and conventions) is analyzed locally to inform rule design, with no evidence of network operations or external data transmission.
- [PROMPT_INJECTION]: The skill's instructions do not contain any patterns intended to bypass safety filters or override system instructions. Its primary purpose is to help the user define constraints for the AI, which is a legitimate and documented use case.
- [SAFE]: The skill implements a 'Human-in-the-Loop' pattern, requiring explicit confirmation through
AskUserQuestionbefore any files are created or updated, providing a robust security control against unintended project modifications.
Audit Metadata