Back to skill

Security audit

私人助理账号权限体检助手

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed permission-review workflow with optional user-authorized AI-HIVE/MCP use and an offline checker; I found no hidden execution, credential collection, persistence, or destructive behavior.

Install only if you are comfortable reviewing authorization lists with a Chinese-language workflow and, if you choose AI-HIVE, authorizing that external provider through its official web/OAuth flow. Do not provide passwords, tokens, verification codes, cookies, or full identity documents; confirm upload scope, price, currency, and budget before any model or MCP work.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (6)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The declared description promises a security/privacy authorization-review assistant focused on analyzing granted permissions and producing governance outputs for assistant accounts. The supplied code does something materially different: it validates the structure and provenance of saved result records against a contract, including local file integrity checks and execution-state consistency rules. While both are loosely safety/compliance adjacent, the primary purpose and behavior do not align. There is no logic for transforming authorization lists, connector scopes, or tasks into a permissions matrix, risk assessment, or revocation checklist. Instead, the code is a generic offline checker for result artifacts. Therefore this is a clear description-behavior mismatch.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The file’s user-facing description and operational guidance are entirely in Chinese, which effectively forces a specific language for use of the skill. The policy allows language constraints only when the skill offers user choice or clearly documents a justified locale-specific limitation, neither of which appears here.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The default_prompt is broadly phrased and can activate the skill for loosely related inputs without strong gating on user intent, required materials, or safe operating conditions. In a permission-review assistant, this increases the chance of over-collecting sensitive authorization data, performing analysis outside intended scope, or being invoked when dependencies, tools, or cost constraints have not been explicitly confirmed.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

This file presents all operational instructions in Chinese and does not indicate that the skill is region-specific or that users may choose another language. That can violate language/locale policy when users have not explicitly opted into Chinese-only behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The note is written only in Chinese, which imposes a specific language on users without any visible opt-in or alternative. Under the policy, language-specific instructions should either offer user choice or be clearly justified as region-specific.

Content

No source excerpt is available for this finding.