nodit-openapi-skill
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted data from external blockchain sources, creating a potential surface for indirect prompt injection.
- Ingestion points: API responses from
web3.nodit.io(e.g., transaction history, token metadata, and entity lookups) defined inreferences/nodit-web3.openapi.json. - Boundary markers: Absent. The instructions do not specify the use of delimiters or provide the agent with guidance to ignore instructions that might be embedded in the retrieved data.
- Capability inventory: The skill uses the
uxctool for network operations and API calls, providing a path for data-driven agent actions. - Sanitization: Absent. There is no evidence of explicit sanitization or filtering of the blockchain content before it is processed by the agent.
- [SAFE]: Authentication is handled securely using environment variables (
NODIT_API_KEY) via theuxc authcommand, avoiding the risk of hardcoded credentials. - [SAFE]: The skill fetches its OpenAPI configuration from the vendor's official GitHub repository (
holon-run/uxc), which is a legitimate and expected source for skill metadata.
Audit Metadata