ClawHub
Back to skill

Security audit

Document Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a simple document-processing skill description with broad but disclosed scope and no executable behavior, persistence, network access, or hidden instructions.

Install this skill if you want Chinese-language document handling assistance. Use it with user-selected documents only, be cautious with confidential or encrypted files, and clarify the desired output language when working in another language.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The skill description and trigger conditions are extremely broad, covering many document types and tasks without clear boundaries, constraints, or safety checks. This can cause the agent to invoke the skill in unintended contexts, increasing the chance of over-collection, mishandling sensitive documents, or use on unsupported/high-risk inputs such as encrypted or repaired files.

Natural-Language Policy Violations

Medium
Confidence
84% confidence
Finding
The skill content is written to operate in Chinese without any user opt-in or locale-selection guidance, which can cause language mismatch during invocation or output generation. In security-sensitive document handling, such mismatches may lead to misinterpretation of extracted content, incorrect summaries, or user confusion about what data is being processed.

Static analysis

No suspicious patterns detected.