nano-check-balance
Pass
Audited by Gen Agent Trust Hub on May 3, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using
bunx,pnpm, ornpxto interact with the Nano protocol via thexno-skillsCLI tool. - [EXTERNAL_DOWNLOADS]: The skill mandates downloading and running the
xno-skillspackage from the npm registry at runtime using the@latesttag. This package is a resource associated with the skill's author. - [PROMPT_INJECTION]: The skill demonstrates an indirect prompt injection surface (Category 8c) because it processes untrusted data from external Nano RPC endpoints to determine account balances.
- Ingestion points: RPC response data (balance and pending amounts) fetched from public nodes such as
https://rainstorm.city/apior user-defined URLs inSKILL.md. - Boundary markers: Absent; the instructions do not specify delimiters to isolate external data from the agent's core instructions.
- Capability inventory: The agent is authorized to execute
xno-skillsCLI commands and perform wallet operations likereceivebased on the state of the ingested data. - Sanitization: No validation or sanitization of the RPC response content is described before interpolation into the agent's context.
Audit Metadata