ClawHub
Back to skill

Security audit

Vibe Research

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed AI-led research workflow with broad autonomy language, but no hidden code, persistence, credential handling, or destructive behavior was found.

Before installing, be aware that this skill encourages the agent to take initiative on research tasks, including pulling sources and proposing analyses. Use it for research where you are comfortable supervising the scope, validating methodology, and checking citations before relying on or publishing results.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill description does not warn users that the agent may autonomously gather data, run analyses, and perform research actions that could affect privacy, external resources, or local system state. Given the skill's explicit design around AI-led execution and 'full-cycle ownership,' users may unknowingly invoke behaviors with meaningful security, integrity, or confidentiality implications.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The activation guidance is broad enough to trigger on many ordinary research or knowledge-gap requests, which can cause the agent to assume 'full-cycle ownership' and autonomously scan literature, gather data, and run analyses in contexts where the user did not explicitly consent to that level of autonomy. In this skill, that risk is amplified by language encouraging proactive execution and independent gap detection, increasing the chance of overreach into privacy-sensitive or system-impacting actions.

Static analysis

No suspicious patterns detected.