Back to skill

Security audit

纯水工艺专员

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent pure-water engineering reference skill with no evidence of code execution, credential access, persistence, or data exfiltration.

Installers should expect a Chinese-first water-treatment engineering assistant. Review technical recommendations before applying them to real systems, especially pharmaceutical, semiconductor, electrical, or compliance-sensitive projects.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (9)

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The entire skill description, examples, and operating instructions are presented only in Chinese, with no indication that users may interact in other languages or that the Chinese-only scope is intentional and justified. Under the policy, a skill that effectively imposes a language/locale without opt-in should be flagged.

Content

No source excerpt is available for this finding.

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The trigger description is broad enough to activate on generic water-treatment or water-quality discussions that may not require this specialized skill. Over-broad routing can cause the agent to invoke the wrong skill, leading to irrelevant guidance, reduced safety checks, or unintended disclosure of specialized operational advice outside the intended scope.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill content is entirely in Chinese and may implicitly bias outputs toward Chinese even when the user has not requested that language. While not a direct code-execution or data-exfiltration issue, forced language behavior can degrade usability, cause misunderstandings in technical or safety-critical instructions, and interfere with higher-priority system locale handling.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill manifest includes both English and Chinese display metadata, but the substantive operating instructions and description are only in Chinese. This can impose a specific language on users without opt-in, which matches the language/locale policy violation criteria.

Content

No source excerpt is available for this finding.

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

The description says to use the skill for 'any mention of pure water system design, ultra-pure water, RO system, EDI system, water treatment process, membrane filtration, or requests to evaluate water quality requirements and design treatment solutions.' Phrases like 'water treatment process' and 'membrane filtration' are broad and lack exclusions or narrower constraints, which could cause unintended invocation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The title and all substantive instructions in the skill are written in Chinese, while the manifest does not state that the skill is region-specific or limited to Chinese-speaking users. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.