ClawHub
Back to skill

Security audit

Bug Bounty

Security checks for vulnerabilities and agentic risk

Overview

The skill is a bug bounty helper, but it encourages vulnerability scanning without requiring authorization, target scope, or safe scanning limits.

Install only if you will use it for systems you own or are explicitly authorized to test. Before invoking scans, define the permitted targets, test window, rate limits, and whether checks must be passive-only.

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 (3)

Missing User Warnings

High
Confidence
96% confidence
Finding
The skill advertises vulnerability scanning and sensitive information discovery but provides no warning that such actions may be intrusive, regulated, or illegal without permission. In this context, omission of safety warnings is particularly risky because the skill is explicitly positioned for offensive security workflows, making misuse more likely and lowering friction for unauthorized scanning.

Natural-Language Policy Violations

Medium
Confidence
94% confidence
Finding
The skill description and usage content are presented entirely in Chinese, with no indication that the user can choose another language or that the locale is intentionally restricted. This can violate language/locale policy when a specific language is imposed without user opt-in or documented justification.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The invocation examples are open-ended and authorize broad actions like scanning arbitrary domains without defining prerequisites such as ownership, authorization, scope limits, or passive-vs-active restrictions. In a security-testing skill, this increases the chance that users invoke active vulnerability scanning against third-party targets, which can cause unauthorized testing, policy violations, or service disruption.

Static analysis

No suspicious patterns detected.