Back to skill

Security audit

ITFE Code Review

Security checks for vulnerabilities and agentic risk

Overview

This is a review-only code review skill with no executable code, persistence, network behavior, or hidden data handling, though it rigidly forces Simplified Chinese output.

Installers should expect reviews and follow-up prompts to be in Simplified Chinese by default and should only use this skill when that language constraint fits their workflow. The skill is otherwise review-focused and does not appear to install code, persist behavior, or modify files without confirmation.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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
98% confidence
Finding

该技能强制要求所有响应仅使用简体中文,且未给用户选择权或说明业务必要性。这会覆盖用户偏好与上层调用约定,降低可用性与可审计性;在安全场景下,还可能被用于限制审查者理解输出内容,从而弱化人工复核。

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

该处再次重复“所有输出必须为简体中文”的硬性要求,说明这不是单一说明性文本,而是被设计为强约束的行为控制。重复约束会增强指令优先级,增加模型忽略用户语言需求或平台策略的概率,影响透明度和可验证性。

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

该工作流要求“所有通信必须使用中文”,直接剥夺了用户与系统在语言上的控制权。在多语言环境或英文安全审计流程中,这会妨碍协作、延误处置,并可能使关键风险信息无法被相关干系人及时理解。

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The default prompt and comments explicitly require all responses to be in Simplified Chinese, including the phrase 'IMPORTANT: Respond in Simplified Chinese' and a file-level language requirement. This is a natural-language locale policy constraint with no user opt-in or alternative language choice documented.

Content

No source excerpt is available for this finding.

Unbounded Output

Medium
Category
Output Handling
Confidence
75% confidence
Finding

Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.

Content

Scanner excerpt · references/code-quality-checklist.md (reported line 107)May include surrounding context.

md
- **Empty string**: Not handled as edge case
- **Whitespace-only string**: Passes truthy check but is effectively empty
- **Very long strings**: No length limits causing memory/display issues
- **Unicode edge cases**: Emoji, RTL text, combining characters

### Common Patterns to Flag