nodus-schema-basics
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted JSON data from external files.
- Ingestion points: The skill operates on .nodus.json files provided to the agent in SKILL.md.
- Boundary markers: None. The instructions do not define markers to separate data from instructions within the JSON objects.
- Capability inventory: The skill utilizes jq for file inspection and legiox-validate-schema for validation.
- Sanitization: No sanitization or filtering of input values is performed before the data is processed by the agent.
Audit Metadata