Back to skill

Security audit

okx-cex-portfolio

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marked this skill suspicious because it flagged guidance about running commands without confirmation; the review is based on incomplete evidence.

Consider the flagged no-confirmation command guidance and review the skill’s command behavior before installing, especially if it can make high-impact changes. Skillspector scanned one Markdown file, but reported incomplete analysis because several local references were missing; the separate AIG scan reported no findings.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

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 275)May include surrounding context.

md
### Step 2: Run read commands immediately — confirm profile (Step 0) then writes

**Read commands** (1–10): run immediately, no confirmation needed.

- `ccy` filter: use currency symbol like `USDT`, `BTC`, `ETH`
- `--instType` for fees/positions: `SPOT`, `SWAP`, `FUTURES`, `OPTION`

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 592)May include surrounding context.

md
## Global Notes

- All write commands require valid credentials (OAuth session or API key in `~/.okx/config.toml`)
- Auth method and trading mode are determined in "Credential & Profile Check"; see that section for parameter rules
- Every command result includes a `[mode: live]` or `[mode: demo]` tag for audit reference
- `--json` returns the raw OKX API v5 response by default. Add `--env` to wrap the output as `{"env": "<live|demo>", "profile": "<name>", "data": <response>}`