Back to skill

Security audit

Highway Lifecycle

Security checks for vulnerabilities and agentic risk

Overview

This is a transparent Chinese-language highway engineering support skill, but its engineering and safety outputs should be treated as advisory.

Use this for Chinese-language highway engineering assistance and model-evaluation workflows, but do not rely on it as the final authority for design compliance, tunnel support changes, traffic safety actions, or maintenance priorities. Have qualified engineers verify standards, field measurements, and safety-critical recommendations, and review any project data before sending it to a model endpoint.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (17)

Tp4

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

The skill advertises broad highway lifecycle analysis capabilities that are not actually implemented, including compliance review, event detection, disease detection, and document consistency auditing. This mismatch is security-relevant because users may rely on the skill for safety-critical engineering review or operational decisions, creating a false sense of assurance and potentially causing unsafe outcomes when the skill only provides limited evaluation guidance.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
80% confidence
Finding

The skill appears to imply file read/write capability without explicitly declaring a scoped permission model. Undeclared capability scope is dangerous because it prevents reviewers and calling systems from understanding what filesystem access the skill may require, increasing the risk of overbroad access or accidental exposure/modification of project files if the skill is integrated with tool execution.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest-style description is entirely in Chinese and presents the skill's invocation guidance, use cases, and trigger phrases only in that language. This creates an implicit language constraint without any user opt-in or explanation that the skill is intended only for Chinese-speaking or China-specific users.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This JSON template labels major sections with Chinese-only natural-language keys such as "评测任务", "模型配置", "数据集", "评测指标", and "结果". That imposes a specific language/locale on users without any opt-in or documented region-specific justification, which matches the language-policy violation criteria.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This JSON template hard-codes Chinese-language domain values such as project types, area types, norms, and bridge types, which effectively constrains use to a specific language/locale. Under the policy, locale-specific constraints should either offer user choice or be clearly documented and justified as region-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The JSON template hardcodes all output field names and expected content in Chinese, which imposes a specific language/locale on skill output. There is no indication that users can choose another language or that the locale restriction is justified by a region-specific requirement.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/multimodal-eval.md (reported line 40)May include surrounding context.

--port 8000

本地调用

curl -X POST http://localhost:8000/v1/chat/completions
-H "Content-Type: application/json"
-d '{"model": "Qwen3-VL-235B", "messages": [...]}'

text

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The document recommends real-time surrounding-rock classification, risk warning, and dynamic support-plan adjustment in a tunnel construction context without an explicit warning that model output is advisory only and must be reviewed by qualified engineers. In a safety-critical civil engineering workflow, overreliance on automated analysis can lead to incorrect support decisions, collapse risk, worker injury, or major infrastructure damage.

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 descriptions and CLI messages that assume Chinese as the only operating language. The policy requires flagging language or locale constraints when the skill forces a specific language without user opt-in or clear justification.

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 content that fixes the skill's interface and documentation to a specific language. The file does not offer any mechanism for user language selection or indicate that the tool is intentionally limited to a Chinese-speaking context.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The function returns user-facing report content exclusively in Chinese, which enforces a specific language for outputs. Under the policy, locale-specific behavior should be opt-in or clearly documented as a justified regional constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The entire guide is written in Chinese and does not indicate that users may choose another language or that the skill is intentionally limited to a Chinese-speaking or region-specific context. Under the language/locale policy, a fixed language without opt-in or justification can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

This markdown file presents all instructions and operational guidance only in Chinese, and it does not state that the skill is region-specific or provide any user opt-in for language/locale. Under the policy criteria, forcing a specific language without user choice can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

This markdown file contains user-facing instructions, prompts, and evaluation guidance exclusively in Chinese. Under the language/locale policy, forcing a specific language without user opt-in or a documented regional justification is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

SQP-3 applies to all file types and covers language or locale policy violations. This file hard-codes a single language for the skill guidance and prompt templates, with no opt-in, alternative locale, or justification that the skill is region-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

All headings, labels, and prompt templates are written exclusively in Chinese, including imperative prompt text such as '分析这张隧道施工截面图' and required output labels, with no indication that the user can choose another language. This constitutes a natural-language locale policy concern unless the file explicitly documents that the skill is intentionally limited to a Chinese-language or China-specific operational context.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

This code file contains user-facing natural language in the module docstring and command-line interface text exclusively in Chinese. Under the policy, forcing a specific language without opt-in is a locale/language policy issue unless the constraint is explicitly justified, which is not present here.

Content

No source excerpt is available for this finding.