nav-deep-interview
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely declarative, providing a framework for structured dialogue without any executable components or tool usage.
- [SAFE]: All references point to local markdown files that provide organizational guidance for Nav projects; no external network requests or downloads are performed.
- [SAFE]: Security instructions explicitly forbid anti-patterns such as logging PII (Personally Identifiable Information) or assuming authentication is unnecessary.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied project descriptions to generate a markdown output. 1. Ingestion points: Step 1 and Step 2 in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: None (text generation only). 4. Sanitization: Absent.
Audit Metadata