Back to skill

Security audit

Manual Qztc

Security checks for vulnerabilities and agentic risk

Overview

This skill locally generates and reviews QZTC teaching manual documents from user-provided Excel and Word files, with no evidence of hidden network access, credential use, or destructive behavior.

Install only if you intend to use it for the QZTC-style Chinese teaching manual workflow. The input spreadsheets and generated Word documents contain student records and grades, so run it only on trusted local files and keep outputs in appropriate protected locations.

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 (6)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding

The skill documents executable commands and clearly implies file read/write behavior, but it does not declare any tool scope such as permissions or allowed-tools. In an agent environment, this can lead to overbroad filesystem access, making unintended reads or overwrites more likely if the skill is invoked with elevated defaults.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description and main heading are entirely in Chinese and present the skill as a general-purpose teaching manual generator, but they do not state that Chinese is optional or that the tool is restricted for a documented locale/compliance reason beyond internal organizational use. This creates a natural-language locale constraint without user opt-in, which matches the policy-violation category.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The module name/comments/docstrings are entirely in Chinese, including the user-facing configuration file header written later by this code. Under the policy, forcing a specific language without opt-in or a documented region-specific justification is a natural-language locale violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This Python file contains user-facing natural-language text entirely in Chinese, beginning with the module docstring and continuing through the CLI help and status output. Under the policy, forcing a specific language without user opt-in is a natural-language locale violation unless the constraint is explicitly justified as region-specific, which is not stated here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This Python file contains natural-language instructions and descriptions entirely in Chinese, including the top-level docstring and usage guidance. Under the policy, forcing a specific language without user opt-in is a locale/language policy violation unless the restriction is explicitly justified, which is not present here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The script prints status, usage, warnings, and errors only in Chinese, which enforces a single language for user interaction. The file does not provide a language flag, locale detection, or documented justification for this restriction.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.