marketing-site-architecture
Pass
Audited by Gen Agent Trust Hub on Aug 8, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is purely informational, providing best practices for site hierarchy, URL structures, and internal linking strategy. No security risks or malicious patterns were identified in the instructions or templates.
- [NO_CODE]: The skill package contains only Markdown files and a JSON evaluation file. It does not include any scripts, binaries, or configuration that would trigger automated command execution or network requests.
- [INDIRECT_PROMPT_INJECTION]: The skill instructions advise the agent to read local context files like
.agents/product-marketing.md. While this constitutes a data ingestion point, the skill possesses no dangerous capabilities or tools for an attacker to exploit via poisoned context files.
Audit Metadata