marketing-site-architecture
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is composed entirely of informational markdown and Mermaid templates. No executable code, scripts, or binaries are included. The provided templates for sitemaps and navigation structures are benign and intended for architectural planning purposes.\n- [PROMPT_INJECTION]: The skill contains instructions to read local configuration files (e.g.,
.agents/product-marketing.md) to gather business context. While this represents an indirect prompt injection surface, the risk is negligible as the skill lacks capabilities for network access, file system modification, or command execution.\n - Ingestion points: SKILL.md reads
.agents/product-marketing.md,.claude/product-marketing.md, andproduct-marketing-context.md.\n - Boundary markers: Absent.\n
- Capability inventory: No tools or scripts capable of file writes, network operations, or subprocess execution are present in the skill.\n
- Sanitization: Absent.
Audit Metadata