ClawHub
Back to skill

Security audit

Wit

Security checks for vulnerabilities and agentic risk

Overview

This is a conversational product-decision framework with no code execution, persistence, credential access, or hidden data handling.

Install this if you want an agent to slow down vague product or strategy discussions and force clearer problem framing before execution. Be aware it may activate in many planning-style conversations, so users may need to ask the agent to skip WIT when they already want implementation or a domain-specific review.

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
96% confidence
Finding

The skill description is broadly scoped across ideas, feature requests, project proposals, vague requirements, process changes, and strategic choices, which overlaps with many generic product and planning conversations. This can cause over-activation or unintended routing, leading the agent to apply this framework in situations where a more specific or safer skill should handle the request, potentially degrading decision quality or bypassing intended specialization.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.