site-architecture
Pass
Audited by Gen Agent Trust Hub on Jul 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is comprised of markdown instructions, ASCII templates, and Mermaid diagram examples. It contains no scripts, binaries, or references to external code execution.
- [SAFE]: The instructions involve reading local marketing context files (e.g., .agents/product-marketing.md) to assist in planning. This is standard behavior for providing context to an AI agent and does not target sensitive system files or credentials.
- [PROMPT_INJECTION]: The skill ingests data from user prompts and local marketing context files, representing an ingestion surface for indirect prompt injection. However, because the skill possesses no tools or capabilities to perform actions such as file writing, command execution, or network access, the presence of untrusted data carries no security risk.
- Ingestion points: User prompts and local project context files like .agents/product-marketing.md (referenced in SKILL.md).
- Boundary markers: None identified.
- Capability inventory: None; the skill's functionality is limited to generating text-based deliverables and Mermaid diagrams.
- Sanitization: None identified.
Audit Metadata