ClawHub
Back to skill

Security audit

Data Analyst Cn

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward Chinese-language data-analysis helper with examples and templates, not a skill that installs code or takes hidden control of the environment.

Install only if you want a Chinese-first data-analysis template skill. Review any generated code before running it, especially code that reads local datasets, queries databases, or fetches API data, and avoid using sensitive files or remote endpoints unless you explicitly intend that access.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill is named and described as a Chinese-specific data analyst skill, and the entire instruction content is written to operate in Chinese without any opt-in or alternative language path. This creates a language policy concern because the skill effectively forces a specific language/locale rather than offering a user choice or documenting a justified region-specific restriction.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The invocation examples are very broad and do not clearly define when the skill should or should not be used. In agent environments, vague triggers can cause over-activation on loosely related prompts, increasing the chance that the skill processes unintended files or generates code/actions beyond the user's actual intent.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill is described as a data analysis assistant, but it includes an example that fetches data from an external API. In a skill context, documenting network access expands the capability boundary from local analysis to outbound data retrieval, which can enable unintended data exfiltration or use of untrusted remote content if adopted by an agent or user without scrutiny.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
88% confidence
Finding

The documented use of requests.get to a third-party URL introduces explicit outbound network communication. Even as an example, this normalizes pulling remote data into the analysis flow and can expose the environment to untrusted content, privacy issues, or accidental transmission patterns in a skill that otherwise appears local-first.

Content

Scanner excerpt · SKILL.md (reported line 68)May include surrounding context.

API

import requests response = requests.get('https://api.example.com/data') df = pd.DataFrame(response.json())

text

Static analysis

No suspicious patterns detected.