Back to skill

Security audit

答应过的事跟进助手

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese-language workflow for turning authorized communication snippets into commitment-tracking drafts and records, with cautious handling of external tools and credentials.

Install this if you are comfortable using a Chinese-language commitment-tracking assistant and only provide materials you are allowed to process. Before using AI-HIVE or any external action, confirm the exact upload scope, price, budget, and authorization; do not paste passwords, tokens, verification codes, cookies, or full identity documents into the workflow.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (7)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

声明描述的是面向承诺跟进的业务型助手,核心行为应是把沟通内容转化为可跟踪输出,并可能依赖工具执行。而给出的代码仅是一个本地验证器,检查结果JSON是否符合输出契约、状态规则、授权与证据约束,并校验本地工件哈希与路径安全。它没有实现所宣称的内容解析、任务跟进、草稿生成或台账生成功能。虽然代码没有出现额外危险的未声明外部能力,但其主要目的与声明严重不符,因此应判定为描述与行为不匹配。

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
79% confidence
Finding

The skill references local files and instructs the agent to read additional materials, but it does not declare an explicit tool scope such as permissions or allowed-tools. This creates a policy gap where an execution environment may grant broader file-read capability than users expect, increasing the risk of unintended access to local reference files or adjacent workspace data.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The manifest description and main skill description are written entirely in Chinese and present the assistant's behavior in that language, with no indication that users may choose another language. This creates a natural-language policy concern because it implicitly constrains the interaction locale without documenting opt-in or a justified region-specific requirement.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The user-facing example inputs and expected outputs are written entirely in Chinese, which indicates the skill behavior is defined around a single language without any visible opt-in or alternative locale handling. Under the stated policy, forcing a specific language without user choice is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The note field is written only in Chinese, which imposes a specific language on users without any opt-in or indication that the skill is intended solely for a Chinese-speaking or region-specific context. This matches the language/locale policy violation category for natural-language content.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The entire document is written in Chinese and does not offer an alternative language or indicate that the locale is intentionally limited to Chinese-speaking users. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

This markdown file presents all operational guidance in Chinese and does not indicate that the user can choose another language or locale. Under the policy rule for natural-language violations, forcing a specific language without opt-in can be a locale-policy issue.

Content

No source excerpt is available for this finding.