Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md - `SKILL.md` keeps scenario routing and confirmation policy.
Security audit
Gate Exchange Unified Account
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed Gate unified-account assistant with sensitive financial write capabilities, but its artifacts keep those actions scoped and require explicit confirmation before any mutation.
Install only if you intend to let the assistant access your Gate unified account through a locally configured MCP session with Unified:Read and Unified:Write permissions. Treat borrow, repay, mode, leverage, and collateral changes as real financial actions; confirm only after checking the draft amount, currency, target mode or setting, and risk note.
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 (13)
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The document requires specific output labels in Chinese and a Chinese warning message at the top when unified account is not enabled. This forces a particular language/locale in responses without user opt-in or justification that the skill is limited to a Chinese-language environment.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The trigger phrases are broad enough to activate the skill on loosely related user requests, increasing the chance that account-management logic is invoked when the user did not clearly intend unified-account operations. In a financial skill that can lead to mutation workflows after follow-up turns, overbroad activation raises the risk of unintended borrowing, repayment, leverage, or collateral-change assistance even if later confirmation gates exist.
- 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: Unified:Read, Unified: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
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 97% confidence
- Finding
The skill mandates Chinese-only output strings for unified mode labels and a required warning banner, regardless of the user's preferred language or locale. This is a natural-language policy issue because it imposes a specific language without offering user choice or documenting a region-specific constraint.
- Content
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 `Unified:Read` and `Unified:Write`. - 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
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The rendering rules require strict mapping of mode labels into Chinese and prescribe a Chinese-only warning banner. This is a natural-language locale constraint that applies globally in the skill, but the document does not offer user opt-in or explain a region-specific requirement.
- Content
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
md 3. Calculate impact note and build `Mode Switch Draft`. 4. After explicit confirmation, execute via `set_unified_mode` and output `Mode Switch Result Report`. **Unexpected Behavior**: 1. Executes mode switch without confirmation. 2. Ignores current mode and submits redundant or wrong target mode. 3. Returns success without showing resulting mode.
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
md 3. Calculate impact note and build `Mode Switch Draft`. 4. After explicit confirmation, execute via `set_unified_mode` and output `Mode Switch Result Report`. **Unexpected Behavior**: 1. Executes mode switch without confirmation. 2. Ignores current mode and submits redundant or wrong target mode. 3. Returns success without showing resulting mode.
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
md 3. Calculate impact note and build `Mode Switch Draft`. 4. After explicit confirmation, execute via `set_unified_mode` and output `Mode Switch Result Report`. **Unexpected Behavior**: 1. Executes mode switch without confirmation. 2. Ignores current mode and submits redundant or wrong target mode. 3. Returns success without showing resulting mode.
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
md 3. Calculate impact note and build `Mode Switch Draft`. 4. After explicit confirmation, execute via `set_unified_mode` and output `Mode Switch Result Report`. **Unexpected Behavior**: 1. Executes mode switch without confirmation. 2. Ignores current mode and submits redundant or wrong target mode. 3. Returns success without showing resulting mode.
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
md 3. Calculate impact note and build `Mode Switch Draft`. 4. After explicit confirmation, execute via `set_unified_mode` and output `Mode Switch Result Report`. **Unexpected Behavior**: 1. Executes mode switch without confirmation. 2. Ignores current mode and submits redundant or wrong target mode. 3. Returns success without showing resulting mode.
Static analysis
No suspicious patterns detected.