Architecture Audit
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes PowerShell commands (e.g., Get-ChildItem, Select-String) to perform its primary function of auditing project files. These commands are used for read-only operations to locate version strings, deprecated terms, and markdown links within the local filesystem.
- [DATA_EXFILTRATION]: While the skill reads project metadata and documentation (package.json, markdown files, source code), it lacks any network capabilities or external URLs. There are no mechanisms present to transmit the gathered data outside the local environment.
- [REMOTE_CODE_EXECUTION]: The documentation mentions automation via npm scripts and GitHub Actions; however, these are provided as implementation examples for the user's own environment rather than executable scripts embedded within the skill itself.
- [PROMPT_INJECTION]: The instructions contain a directive to ignore the
.github/folder during audits. This is a scope-limiting constraint specific to the auditing task and does not attempt to bypass agent safety filters or override core system instructions.
Audit Metadata