ClawHub
Back to skill

Security audit

Research Pro

Security checks for vulnerabilities and agentic risk

Overview

This is a plain markdown research-workflow skill with no executable code, persistence, credential handling, or hidden behavior.

Install this if you want a Chinese-first structured research workflow. Before using it for experiments or paper writing, keep code execution, database lookup, and publication claims under your own review, and confirm citations and results independently.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (2)

Natural-Language Policy Violations

Medium
Confidence
88% confidence
Finding
The description and examples are Chinese-only and do not offer a language-choice mechanism, which can cause misrouting or unexpected behavior for users interacting in other languages. This is not a direct security exploit by itself, but it can weaken user understanding and consent, especially if the skill activates and proceeds in a language the user did not choose.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger phrases are overly broad and map to common, ordinary research-related conversation, which can cause the skill to activate unintentionally during benign user requests. In a powerful workflow skill that spans literature review, code generation, experiment execution, and paper writing, accidental activation can redirect the assistant into an unintended multi-step process and increase the chance of unsafe tool use or user confusion.

Static analysis

No suspicious patterns detected.