site-architecture
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of markdown instructions and templates. No executable scripts, binaries, or automated tools are included in the package.
- [INDIRECT_PROMPT_INJECTION]: The instructions recommend reading local marketing context files (e.g.,
.agents/product-marketing.md) if available. While this defines a data ingestion surface, the skill lacks any capabilities (such as network tools, file-writing tools, or code execution) that could be used to exploit this surface for data exfiltration or unauthorized actions.
Audit Metadata