okx-agentic-wallet

Fail

Audited by Snyk on May 13, 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 instructs the agent to display API keys (and to echo verification codes/keys in CLI commands) — requiring the LLM to output sensitive secrets verbatim, which is an exfiltration risk.

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

  • Third-party content exposure detected (high risk: 0.90). The skill's required pre-flight (see _shared/preflight.md) mandates calling the public GitHub API (https://api.github.com/repos/okx/onchainos-skills/releases/latest) and downloading installer scripts/checksums from raw.githubusercontent.com/releases — mandatory runtime fetching and execution of public repository content that directly influences installation and subsequent agent behavior exposes it to untrusted third-party content.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 1.00). The skill's shared preflight explicitly runs runtime fetch-and-execute commands (e.g., curl -sSL "https://raw.githubusercontent.com/okx/onchainos-skills/${LATEST_TAG}/install.sh" -o /tmp/onchainos-install.shthensh /tmp/onchainos-install.sh`) so it fetches remote code from raw.githubusercontent.com and executes it as a required installation step.

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

  • Direct money access detected (high risk: 1.00). The skill is expressly a crypto wallet / on-chain transaction executor. It defines explicit commands for sending native tokens and ERC‑20/SPL tokens (onchainos wallet send), performing contract calls (onchainos wallet contract-call), signing (personalSign, EIP‑712, TEE signing), exporting wallets, managing Gas Station (enable/disable/update-default-token/setup) and other on‑chain write operations. These are specific crypto/ blockchain financial actions (wallet transfers, swaps/contract interactions, signing and broadcasting txs), not generic tooling. Therefore it grants Direct Financial Execution authority.

Issues (4)

W007
HIGH

Insecure credential handling detected in skill instructions.

W011
MEDIUM

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

W012
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

W009
MEDIUM

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

Audit Metadata
Risk Level
HIGH
Analyzed
May 13, 2026, 08:49 PM
Issues
4