agentic-wallet

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). This skill requires including a one-time password (OTP) verbatim in shell commands (e.g., npx awal auth verify <otp>), which instructs the agent to handle and output a secret-like value directly, creating an exfiltration risk.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). The runtime workflow reads outsider-authored free text via references/x402-search.md, where user-supplied <query> is sent to npx awal@2.12.0 x402 bazaar search <query>, and the agent also ingests bazaar-listed service metadata/results during search/list/details.

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

• Direct money access detected (high risk: 1.00). The skill explicitly exposes crypto wallet and payment commands (via the awal CLI) that perform financial actions: sending tokens, swapping/trading tokens, adding/funding (onramp/buy USDC), and paying USDC to call paid endpoints. These are specific, purpose-built financial execution capabilities (e.g., npx awal ... send, trade, x402 pay), not generic tools, so this grants direct financial execution authority.