ClawHub
Back to skill

Security audit

Group Buy Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a simple shopping-assistance skill that gives group-buy estimates and share text, with no code, persistence, credential access, or hidden system behavior.

Before installing, understand that the skill provides rough shopping-strategy estimates and persuasive share text, not official platform probabilities or financial advice. Users should provide key campaign details and treat generated recruitment copy as something to review before sending.

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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The invocation text is broadly scoped and can trigger on a wide range of shopping-related requests such as analysis, estimation, recommendation, and copy generation without strong exclusion criteria. That increases the chance of unintended activation, causing the skill to steer conversations into persuasive recruitment or quasi-financial advice when the user may not have explicitly asked for this specific capability.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The skill title, examples, and usage phrases are heavily Chinese-specific, and the documented invocation patterns are all in Chinese without offering a language choice. This can violate language or locale policy if the skill assumes a specific language rather than letting the user choose.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.