architect-review
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is composed entirely of instructional text to establish a specific AI persona (Software Architect). It does not contain any functional code or system-level instructions.
- [NO_CODE]: No scripts or binaries are included with this skill. It operates solely as a prompt template, which eliminates risks associated with package vulnerabilities or malicious execution.
- [EXTERNAL_DOWNLOADS]: Analysis confirmed that the file contains no URLs, download commands (like curl or wget), or external resource references.
- [PROMPT_INJECTION]: The instructions are focused on architectural expertise and do not attempt to bypass safety filters, override system prompts, or extract sensitive model information.
Audit Metadata