ClawHub
Back to skill

Security audit

Qualify

Security checks for vulnerabilities and agentic risk

Overview

This is a plain decision-framework skill for qualifying opportunities and requests, with no code execution or hidden access behavior found.

This skill is reasonable for structuring sales, client intake, project, recruiting, or request-screening decisions. Treat its outputs as a framework, not final authority, especially for legal, HR, procurement, medical, financial, compliance, or regulated decisions where specialized review is still needed.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger conditions are overly broad and can match many generic decision-making or filtering requests, causing this skill to activate outside its intended niche. That creates routing and prompt-injection surface area by letting a qualification framework steer unrelated high-stakes decisions such as HR, legal, compliance, or safety-sensitive triage where domain-specific controls should take precedence.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.