Back to skill

Security audit

okx-cex-bot

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill suspicious with medium confidence, mainly because it flags a concern about instructions that may allow high-impact actions without asking first.

Consider whether you are comfortable with the flagged concern about actions potentially being taken without confirmation, and check how the MCP server version is controlled before installing. The scan is incomplete: three local references were unresolved, so the evidence does not cover those references.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

MCP server referenced without pinned version: 'nPx and'.

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

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 · references/dca-commands.md (reported line 206)May include surrounding context.

md
- **INVALID_PRICE_STEPS_MULTIPLIER error**: adjust `slPct`. Recalculate MPD = Σ(pxSteps × pxStepsMult^i) for i = 0..maxSafetyOrds−1, then set `slPct` > MPD
- **algoClOrdId duplicate**: error code `51065`
- **Margin adjustment blocked by pending close order (`59302`)**: `bot dca add-margin`/`reduce-margin` fails if the position has a pending close order. Tell the user to cancel the pending close order first, then retry
- **Margin adjustment out of range (`59301`)**: `bot dca add-margin`/`reduce-margin` fails if the adjustment would push margin outside the allowed range. Report the error; do not retry with an arbitrary different amount without asking the user
- **Sync copy-trading follower blocked (`51223`)**: `bot dca update-tp` is not available for sync copy-trading follower accounts (`copyType=2` + `trackingMode=sync`). Explain this to the user rather than retrying

---