Back to skill

Security audit

platform-pitfalls

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only skill about Windows encoding and C++ coroutine pitfalls, with no hidden execution, persistence, or data access behavior found.

Install only if you want Chinese/UTF-8 Windows troubleshooting and C++ coroutine pitfall guidance. When applying the snippets, review environment and console changes such as chcp 65001, PYTHONIOENCODING, and VSLANG=1033 because they may affect diagnostics or terminal behavior for that command/session.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (5)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
82% confidence
Finding

The text states that validation 'only counts' on Chinese Windows and Windows runners, which imposes a specific locale/platform expectation in natural language. The README does not present this as an optional or region-specific mode, nor does it offer user choice or clearly justify the locale constraint as a compliance requirement.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The example string explicitly instructs the user to send Chinese text to their AI ("请复制以下内容发给你的AI"), and the document overall is written as a Chinese-only workflow without any language-choice guidance. Under the policy rule, forcing a specific language without user opt-in is a natural-language locale/language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

Lines L027-L032 explicitly set VSLANG="1033" and describe forcing diagnostics to English. This is a natural-language locale constraint applied unconditionally, and the document does not present it as optional or user-selectable.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

Line L099 says MSVC 的英文诊断靠 VSLANG=1033, reinforcing that English diagnostics are required. Because the file does not offer an alternative locale choice or explicit opt-in, this is a language-policy violation under the stated rule.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The title and the entire skill content are written in Chinese, which imposes a specific language on users without any visible opt-in or alternative language option. Under the stated policy, forcing a language or locale without user choice is a natural-language policy violation unless it is clearly documented as region- or audience-specific.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.