ClawHub
Back to skill

Security audit

企业数字化转型顾问

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese-language digital transformation advisor that uses a bounded public search helper for reference metadata and does not show hidden credential access, persistence, destructive behavior, or data exfiltration beyond its stated search purpose.

Before installing, users should understand that the skill is written for Chinese-language consulting workflows and may contact api.cgltzk.vip to search public reference metadata. Avoid giving it confidential client details for search, and keep using the documented boundary: generic keywords only, no downloads or login bypass attempts.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • 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
Findings (10)

Credential Access

High
Category
Privilege Escalation
Content
__pycache__/
*.py[cod]
.venv/
.env
.env.*
Confidence
60% confidence
Finding
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding
The description presents a business consulting/planning skill with broad enterprise digital-transformation analysis and document-generation capabilities, optionally using a public search interface for references. The actual code does not implement any of those consulting functions. Instead, it is strictly a unit test file for a search helper, checking sanitization, filtering, redirect suppression, oversized/invalid response handling, and HTTP error behavior. While it relates loosely to the declared mention of searching reference materials, that is only a small supporting aspect; the code’s primary purpose is test validation of the search contract, making the description materially inaccurate for this code chunk.

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill instructs the agent to use a public search interface and even references running a bundled script or calling an external API, but it declares no explicit tool scope or allowed-tools boundary. That creates an authorization gap where network access may be available implicitly, making review, containment, and least-privilege enforcement weaker than intended.

Natural-Language Policy Violations

Medium
Confidence
91% confidence
Finding
The manifest description and the entire user-facing instructions are written exclusively in Chinese, indicating the skill is intended to operate in Chinese by default. There is no stated option for the user to choose another language, nor a documented region-specific justification for enforcing this locale.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The manifest includes a natural-language default prompt that invokes the skill with a general request to design a digital transformation plan and find matching references, but it does not define specific trigger boundaries or exclusion conditions. In a manifest file, this kind of broad invocation wording can contribute to ambiguous activation behavior if used as a trigger example without narrower constraints.

Natural-Language Policy Violations

Medium
Confidence
94% confidence
Finding
The entire skill file is written in Chinese and does not indicate that language selection is optional or that other locales are supported. Under the policy, forcing a specific language without user opt-in is a natural-language locale violation unless the constraint is explicitly documented and justified.

Natural-Language Policy Violations

Medium
Confidence
85% confidence
Finding
The entire skill is written as prescriptive operational guidance in Chinese and does not indicate that users may choose another language or locale. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern unless the locale restriction is explicitly justified.

External Transmission

Medium
Category
Data Exfiltration
Content
from urllib.parse import urlencode
from urllib.request import HTTPRedirectHandler, Request, build_opener

ENDPOINT = 'https://api.cgltzk.vip/mapp/search/'
MAX_BYTES = 2_000_000
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
from urllib.parse import urlencode
from urllib.request import HTTPRedirectHandler, Request, build_opener

ENDPOINT = 'https://api.cgltzk.vip/mapp/search/'
MAX_BYTES = 2_000_000
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Natural-Language Policy Violations

Low
Confidence
96% confidence
Finding
This code hard-codes user-facing validation errors in Chinese, and similar Chinese-only messages appear throughout the script output. That creates a language policy issue because the skill does not offer a language choice or document that it is intentionally limited to a Chinese-language context.

Static analysis

No suspicious patterns detected.