Back to skill

Security audit

培训纪要结构化手册

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed training-transcript summarizer that reads user-provided or tmeet-provided meeting content and generates a Markdown training handbook.

Install only if you are comfortable with a Chinese-language workflow and with giving the agent or tmeet access to the meeting transcripts you want summarized. Review generated handbooks and quiz questions before using them for formal training or assessment.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The entire skill description, examples, commands, and outputs are presented only in Chinese, and the skill name itself is Chinese. There is no indication that users may choose another language or that the skill is intentionally limited to a Chinese-only compliance or regional context, which creates a natural-language locale policy concern.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding

The skill instructs the agent to read user-provided transcription/minutes files in a 'local mode' and to generate a Markdown handbook, which implies file read and file write behavior, but the manifest does not declare any explicit tool scope or permissions. Undeclared capabilities make it harder to enforce least privilege and can let the skill access or create files more broadly than reviewers or the runtime expect.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This code file contains natural-language instructions and output that are entirely fixed to Chinese, including the module docstring and generated content. Under the policy rule, forcing a specific language without user opt-in is a locale/language policy violation unless the constraint is explicitly justified, which is not stated here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

该培训手册全文仅以中文呈现,且未说明是否支持其他语言,也没有提供用户选择语言的选项。根据规则,强制特定语言而无用户选择或明确合理说明,属于自然语言层面的语言/locale policy 问题。

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

This markdown template presents all user-facing instructions and content structure in Chinese, which can constitute a language policy issue when no alternative language option or opt-in is provided. The file does not indicate that the Chinese-only format is region-specific or explicitly chosen by the user.

Content

No source excerpt is available for this finding.