naval-almanack
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user queries to route to specific internal markdown files. While it interacts with untrusted user input, it lacks dangerous capabilities such as network access, file modification, or command execution. Additionally, each reference file contains a dedicated 'Boundary' section that explicitly defines scope and limitations, which serves as a safeguard against instruction override. Severity: SAFE.
- [SAFE]: No network operations, sensitive file path access, or hardcoded credentials were found in the skill files or metadata.
- [SAFE]: The skill does not contain any executable scripts (Python, Node.js, or shell) or external dependencies. All logic is implemented via static markdown instructions for the AI agent.
- [SAFE]: No obfuscation techniques, hidden URLs, or persistence mechanisms were detected in the analyzed files.
Audit Metadata