nano
Fail
Audited by Snyk on May 6, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). The prompt explicitly permits and documents a CLI signing flow that embeds a user's raw private key (hex) as a --key argument, which requires the LLM to accept and emit secret values verbatim (an exfiltration risk).
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill explicitly relies on public zero-config RPC nodes (e.g., https://rainstorm.city/api and https://nanoslo.0x.no/proxy) used automatically by xno-mcp to fetch account balances, pending transactions, history, and other runtime data which the agent must read and act on (e.g., calling receive/send), so untrusted third-party responses can materially influence its actions.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill instructs fetching and executing remote code at runtime via the npm package reference (e.g., "bunx -y xno-skills@latest" / "pnpm dlx xno-skills@latest" / "npx -y xno-skills@latest"), which downloads and runs external code (xno-skills@latest) as a required CLI fallback.
MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).
- Direct money access detected (high risk: 1.00). The skill is explicitly a Nano (XNO) wallet operator with built-in, specific financial actions. It defines and mandates use of MCP/CLI tools such as "send", "receive", "wallets", "payment_request_create", "payment_request_receive", and "payment_request_refund" (including an execute=true refund), and provides CLI send commands. It describes signing, PoW, and broadcast behavior (OWS-backed signing) and even allows overriding spending limits via config_set. These are concrete cryptocurrency wallet operations that move funds and manage transactions — not generic tooling. Therefore it grants direct financial execution authority.
Issues (4)
W007
HIGHInsecure credential handling detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
W009
MEDIUMDirect money access capability detected (payment gateways, crypto, banking).
Audit Metadata