nano-request-payment
Pass
Audited by Gen Agent Trust Hub on May 3, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches the
xno-skillsand@open-wallet-standard/corepackages from the npm registry during execution. - [REMOTE_CODE_EXECUTION]: The skill instructs the agent to download and execute code from the npm registry using
npx -y,bunx -y, orpnpm dlx. It specifically requests the@latestversion ofxno-skills, meaning the executed code is not pinned to a specific hash or version. - [PROMPT_INJECTION]: The skill processes untrusted user input that could lead to indirect prompt injection.
- Ingestion points: The
reasonandwalletNameparameters in thepayment_request_createtool are populated by user-provided text. - Boundary markers: No delimiters or instructions are provided to the agent to treat this data as untrusted.
- Capability inventory: The agent can check balances, create payment requests, and broadcast blocks to receive funds using the
xno-skillsCLI. - Sanitization: No validation or sanitization of the input strings is mentioned in the instructions.
Audit Metadata