Back to skill

Security audit

个人邮箱分流与漏信检查助手

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese-language inbox triage helper with read-only defaults, explicit authorization gates for mailbox changes, and an offline validation script that fits its stated workflow.

Before installing, confirm you are comfortable using a Chinese-language workflow that may process sensitive mailbox exports or connect to AI-HIVE via OAuth/MCP. Use a narrow mailbox scope, do not paste passwords, tokens, cookies, or verification codes, and require explicit approval before any labels, sends, payments, deletions, uploads, or paid model calls.

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 (7)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The declared description is about an email-management assistant operating on mailbox contents and producing email-related outputs. The supplied code does something materially different: it validates offline result records for structural correctness, provenance fields, execution metadata, and local artifact hashes. It does not connect to any mailbox, process emails, classify messages, generate the promised email deliverables, or invoke AI/MCP/tooling. This is not merely an implementation detail; the primary purpose is unrelated to the declared skill behavior.

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
93% confidence
Finding

The user-facing description and heading content are entirely in Chinese, presenting the skill as operating in that language by default. There is no statement that users may choose another language or that the Chinese-only presentation is a justified locale constraint, which can violate language-choice policy.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The display name, description, and default prompt are all written in Chinese, which implies the skill is designed to operate in a fixed language without indicating user opt-in or a justified locale restriction. This may violate language or locale policy when no choice or limitation is documented.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The default activation prompt is broadly phrased and can trigger the skill for a wide range of loosely related requests without requiring explicit confirmation of mailbox scope, account selection, or tool availability. In an email-triage context, this increases the chance of over-collection, unintended processing of sensitive mailbox content, or premature execution against the wrong dataset or account.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The file's natural-language instructions are entirely in Chinese, and there is no indication that users can opt into another language or that the skill is intentionally limited to a Chinese-speaking or region-specific context. This can violate language/locale policy by forcing a specific language without user choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The natural-language note is written only in Chinese, which imposes a specific language on users reading or filling the manifest. The file does not provide an alternative language option or explain that the skill is intended only for Chinese-speaking or region-specific use.

Content

No source excerpt is available for this finding.