align-architecture
Pass
Audited by Gen Agent Trust Hub on Mar 16, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill instructions are strictly focused on architecture compliance tasks and do not contain any instructions to override safety guidelines or bypass behavioral constraints.
- [DATA_EXFILTRATION]: The skill operates entirely on local project files. It reads documentation from paths like
docs/architecture/and reads source code for comparison. It writes an Architecture Compliance Report todocs/calibration/. No network requests or access to sensitive system paths (e.g., ~/.ssh) were identified. - [REMOTE_CODE_EXECUTION]: No remote code execution patterns were found. The skill does not download or execute scripts from external URLs.
- [COMMAND_EXECUTION]: The skill does not trigger any arbitrary shell commands or subprocesses. Its logic is based on parsing text and analyzing file content.
- [EXTERNAL_DOWNLOADS]: There are no runtime external downloads or dependency installations. The installation command mentioned in the README is standard for the ai-cortex ecosystem and points to the vendor's own repository.
Audit Metadata