Back to skill

Security audit

okx-cex-smartmoney

Security checks for vulnerabilities and agentic risk

Overview

This OKX skill is a disclosed, read-only smart-money analytics helper that uses the OKX CLI and local OKX authentication state without evidence of hidden writes, trading, exfiltration, or persistence.

Install only if you are comfortable letting the OKX CLI access your local OKX authentication/profile state for read-only smart-money analytics. Do not paste OKX API keys into chat, verify the npm package provenance, and keep trading/transfer permissions separate from analytics use where possible.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
70% confidence
Finding

Skill instructs the agent to never refuse or to always comply. Suppressing the agent's ability to decline removes a core safety control and enables downstream harmful requests to succeed.

Content

Scanner excerpt · SKILL.md (reported line 153)May include surrounding context.

md
- **Security:** Never ask users to paste API keys or secrets into chat.
- **Output:** Always pass `--json` to list/query commands and render results as a Markdown table — never paste raw terminal output.
- **Network errors:** If commands fail with a connection error, prompt user to check VPN: `curl -I https://www.okx.com`
- **Language:** Always respond in the user's language.
- **Time inputs:** `signal-trend-by-{filter,trader}` take an optional `--asOfTime <yyyyMMddHH>` anchor (10-digit UTC hour); omit to use the current UTC hour. `--limit` controls how many buckets are returned ending at that anchor. `signal-overview-by-{filter,trader}` takes no time input — handler always uses the current hour.

For number/time formatting and response structure conventions, read `{baseDir}/references/templates.md`.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 142)May include surrounding context.

md
### Step 2 — Execute and present

All commands are READ-only — no confirmation needed. Always pass `--json` and render results as Markdown tables.

For multi-step workflows (recommend traders then drill down, signal analysis with context), read `{baseDir}/references/workflows.md`.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 150)May include surrounding context.

md
## Global Notes

- **Security:** Never ask users to paste API keys or secrets into chat.
- **Output:** Always pass `--json` to list/query commands and render results as a Markdown table — never paste raw terminal output.
- **Network errors:** If commands fail with a connection error, prompt user to check VPN: `curl -I https://www.okx.com`
- **Language:** Always respond in the user's language.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

In the parameter table for trader-orders-history, --after is described as returning orders before an ordId, while --before is described as returning orders after an ordId. This is the inverse of the flag names and conflicts with the surrounding pagination conventions used elsewhere in the same document, so the documentation actively misstates the tool's intended behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The field description uses Chinese terms in sz (币 for SPOT, 张 for SWAP/FUTURES) within an otherwise English reference. This introduces a locale-specific presentation choice without stating that the skill is Chinese-localized or offering an alternative, which can violate language/locale consistency policy.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The workflow repeatedly presents user utterances only as Chinese/English examples, which implicitly constrains interaction languages without explicitly offering a language choice. This can conflict with a language/locale policy that requires user opt-in or clear flexibility rather than assumed bilingual support only.

Content

No source excerpt is available for this finding.