ns-agent-architecture
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions provide shell commands for the agent to execute a bundled Python utility script for scaffolding documentation files.- [DYNAMIC_EXECUTION]: The skill utilizes a provided Python script to extract content from templates and generate project-specific architecture specifications at runtime.- [INDIRECT_PROMPT_INJECTION]: The Reverse mode feature allows the agent to ingest project code and metadata to document existing systems, which creates a data ingestion surface.
- Ingestion points: The skill reads graph nodes, tools, and local documentation files such as docs/context/system-reverse-spec.md.
- Boundary markers: No specific delimiters are implemented to isolate ingested data from the agent's internal logic.
- Capability inventory: The skill is capable of performing local file writes and executing shell-based Python scripts.
- Sanitization: Content read from external files is processed directly without sanitization or escaping mechanisms.
Audit Metadata