architect
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a structured workflow for architectural design that emphasizes planning and human-in-the-loop validation. It does not include any commands for network access, credential harvesting, or unauthorized file system operations.- [SAFE]: No obfuscation, encoding, or hidden instructions were found in the skill files or metadata. The instructions are clear and purpose-oriented.- [INDIRECT_PROMPT_INJECTION]: The skill possesses a standard attack surface for coding agents by ingesting project code and documentation. However, the multi-phase design process (including an optional human checkpoint) provides inherent safety layers against malicious instructions embedded in the processed data.- [SAFE]: All external skill references are local or relative, and the skill specifically disables model invocation via frontmatter configuration, reducing the automated execution footprint.
Audit Metadata