ClawHub
Back to skill

Security audit

Report To Visualization

Security checks for vulnerabilities and agentic risk

Overview

This skill is a markdown-only formatter that turns Chinese report text into a strict visualization JSON format, with no evidence of hidden execution, persistence, credential access, or data exfiltration.

Install this if you want Chinese report-to-visualization formatting with a strict seller-report JSON schema. Be aware it may take over broad requests like "visualize this report" and will likely produce Chinese, tightly constrained output.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill advertises broad trigger phrases like “可视化报告”, “用图表展示”, and “图文并茂”, which are common user expressions and can cause the agent to invoke this skill in situations where the user did not intend a strict visualization-only transformation. Because the skill then imposes rigid output and formatting behavior, accidental activation can suppress normal assistant behavior and route unrelated content into a constrained pipeline.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill hard-codes Chinese-language instructions and output expectations across the entire file without stating a locale precondition or requiring user opt-in. If invoked for users operating in another language, it can override user preferences, reduce transparency, and produce unusable or misleading results, especially because the output format is already strict and leaves little room for recovery.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The file is entirely written as mandatory instructions in Chinese and presents strict constraints without offering any language or locale choice. Under the stated policy, forcing a specific language is a natural-language policy violation unless the locale constraint is explicitly documented and justified as region-specific.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.