Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md - `SKILL.md` keeps transfer intent routing and account-type mapping.
Security audit
Gate Exchange Transfer
Security checks for vulnerabilities and agentic risk
Overview
This is a clearly scoped Gate internal-transfer helper that can move funds only after explicit confirmation, but it does require wallet write access to the user's Gate account.
Install only if you intend to let the agent perform Gate same-UID internal transfers through your configured MCP account. Use a Gate API key limited to the listed permissions, verify every transfer draft carefully, and do not confirm unless the amount, asset, source, and destination are exactly right.
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
- 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)
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The trigger phrases in the manifest description are broad enough to match common finance requests such as 'transfer funds' or 'internal transfer' without tightly constraining destination, platform, or account ownership. In a wallet-transfer skill with write permissions, overbroad routing can cause the assistant to invoke this skill in unintended contexts, increasing the chance of confusing or unsafe fund-movement flows.
- Content
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
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
md - Credentials Source: Local Gate MCP deployment (`GATE_API_KEY`, `GATE_API_SECRET`) - API Key Required: Yes - Permissions: Delivery:Read, Fx:Read, Margin:Read, Options:Read, Spot:Read, Wallet:Write - 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
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
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 permissions for this skill are `Wallet:Write`, `Spot:Read`, `Margin:Read`, `Fx:Read`, `Delivery:Read`, and `Options:Read`. - If the required Gate MCP tools are missing, stop write actions and switch to setup guidance only. - If the MCP session returns an auth or permission error, stop write actions and guide the user to repair the configured local MCP credentials before continuing.
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 81% confidence
- Finding
The skill specifies explicit confirmation examples only in English ('Confirm' / 'Yes'), which can impose a language expectation without opt-in. This may conflict with language/locale policy if users interact in another language and the skill does not state that equivalent confirmations in the user's language are accepted.
- Content