site-architecture
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists exclusively of markdown instructions and Mermaid diagram templates. It does not utilize any tools, scripts, or system-level commands.- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read local project context files (e.g., .agents/product-marketing.md), which establishes a potential ingestion surface for untrusted data. However, the risk is negligible as the skill lacks any capabilities to execute code, write files, or exfiltrate data.
- Ingestion points: Reads project context from .agents/product-marketing.md or similar files (documented in SKILL.md).
- Boundary markers: Absent.
- Capability inventory: None; the skill has no tool permissions or shell execution capabilities.
- Sanitization: Absent.
Audit Metadata