Back to skill

Security audit

okx-cex-earn

Security checks for vulnerabilities and agentic risk

Overview

This skill is for real OKX Earn account actions and is mostly coherent, but its live financial write workflows have a confirmation gap for Dual Investment purchases that users should review carefully.

Install only if you intend to let an agent use your live OKX account for Earn workflows. Review DCD purchases carefully, require the assistant to restate product ID, amount, currency, yield, term, conversion/settlement outcomes, and obtain a clear yes/no before any quote-and-buy command. Use a least-privilege OKX profile and stop any /loop monitors when no longer needed.

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
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (14)

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 231)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.

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

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · references/savings-commands.md (reported line 222)May include surrounding context.

md
**NEVER expose raw state values** to the user — always translate using the table above.

**Display rules:**
- Render as Markdown table with columns: # · reqId · Currency · Amount · Rate · Term · Status · Accrued Interest · Create Time
- Format timestamps using `YYYY/M/D HH:MM`
- For `pending` orders, note that early redemption is available

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill description contains a very broad set of trigger phrases, including generic concepts like idle funds, earning, savings, staking, and term deposits. This can cause the agent to invoke a high-risk financial skill in ambiguous contexts, increasing the chance of unintended authenticated actions or inappropriate financial guidance in the wrong workflow.

Content

No source excerpt is available for this finding.

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 228)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.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

This section documents a buy flow (quote-and-buy) that places a live financial order but does not require an explicit user confirmation step or a prominent warning that the action commits funds and may convert assets at settlement. In an agent setting, ambiguous user intent or UI misrendering could cause the assistant to execute an account-affecting trade immediately, creating real financial loss risk.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The redeem-execute flow is explicitly immediate and internally performs both quote retrieval and execution, yet the documentation lacks a clear warning that this is an irreversible account-affecting action that can realize gains or losses. In an autonomous or semi-autonomous agent workflow, this increases the chance of accidental redemption without informed consent, especially because the command abstracts away the usual two-step review process.

Content

No source excerpt is available for this finding.

Behavior Manipulation

Medium
Category
Prompt Injection
Confidence
75% confidence
Finding

Subtle instructions detected that may alter agent decision-making or introduce hidden biases.

Content

Scanner excerpt · references/savings-commands.md (reported line 63)May include surrounding context.

okx --profile live earn savings set-rate --ccy USDT --rate 0.01

text

`--rate` is the user's minimum matching threshold — funds are lent only when the market lending rate ≥ this value. The actual yield is always `lendingRate`. Never tell users that lowering their minimum rate reduces earnings — this is incorrect.

---

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

The file contains a natural-language instruction to convert timestamps to the user's timezone, but if that is unknown, to default to UTC+8. This hard-codes a locale choice that may misrepresent times for users in other regions and does not provide an opt-in or justified region-specific constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The instruction explicitly requires a specific language behavior: 'Respond in the user's language.' Under the policy, language/locale constraints should not be forced unless the skill offers a choice or clearly documents a justified locale limitation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

This line again instructs the skill to 'Respond in the user's language,' which is a natural-language policy issue when no language choice or opt-in is provided. The file does not frame this as optional or user-configurable.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The workflow includes a mandatory language directive rather than an opt-in or configurable preference. Per the policy, this should be offered as a choice unless there is a documented justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

This is another repeated language-policy instruction that constrains output language without explicit user choice. Repeated mandatory locale behavior across the workflow increases the chance of inconsistent policy compliance.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The line directs the assistant to provide the explanation in the user's language, but the file does not offer a language preference mechanism. That fits the language/locale policy violation category.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

This instruction imposes a response-language constraint without user opt-in or documented necessity. The policy calls for offering a choice or clearly justified locale restriction.

Content

No source excerpt is available for this finding.