ClawHub
Back to skill

Security audit

Gate Exchange Affiliate Program Skill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a read-only Gate affiliate reporting assistant that uses disclosed Gate MCP credentials and scoped rebate tools to show partner commission, transaction, referral, and application data.

Install only if you intend the agent to access your Gate partner rebate data through a locally configured Gate MCP session. Use a key limited to Rebate:Read, be aware reports can include referral users, commissions, trading volume, fees, and application status, and double-check any query triggered only by the generic word "commission" or by relative dates interpreted in UTC+8.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (6)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 72)May include surrounding context.

md
- `SKILL.md` keeps routing and reporting policy.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger phrase 'commission' is overly broad and can cause this affiliate skill to activate for unrelated financial or employment questions. That misrouting can expose partner-only data paths or cause the agent to use affiliate tooling in contexts the user did not intend, increasing the risk of unintended data access or confusing disclosures.

Content

No source excerpt is available for this finding.

Unrestricted Tool Access

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.

Content

Scanner excerpt · SKILL.md (reported line 31)May include surrounding context.

md
## General Rules

⚠️ STOP — You MUST read and strictly follow the shared runtime rules before proceeding.
Do NOT select or call any tool until all rules are read. These rules have the highest priority.
→ Read `./references/gate-runtime-rules.md`
- **Only call MCP tools explicitly listed in this skill.** Tools not documented here must NOT be called, even if they
  exist in the MCP server.

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 60)May include surrounding context.

md
- Credentials Source: Local Gate MCP deployment (`GATE_API_KEY`, `GATE_API_SECRET`)
- API Key Required: Yes
- Permissions: Rebate:Read
- Never ask the user to paste secrets into chat; rely on the configured MCP session only.
- API Key Provisioning Reference: https://www.gate.com/myaccount/profile/api-key/manage (create or rotate keys outside the chat when the local MCP setup requires them).

### Installation Check

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The instructions state that all query windows use the user's current calendar date in UTC+8, and later repeat that all relative time calculations must be based on UTC+8. This forces a specific locale/timezone policy on every user without opt-in or a clear region-specific justification.

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 · references/gate-runtime-rules.md (reported line 16)May include surrounding context.

md
## 1. MCP Session and Authentication

- Use the already configured Gate MCP session for the current host.
- Local Gate MCP deployments use `GATE_API_KEY` and `GATE_API_SECRET`; never ask the user to paste these secrets into chat.
- Minimal permission for this skill is `Rebate:Read`.
- If the required Gate rebate tools are missing, stop and switch to setup guidance only.
- If the MCP session returns an auth or permission error, stop and guide the user to repair the configured local MCP credentials before continuing.

Static analysis

No suspicious patterns detected.