ClawHub
Back to skill

Security audit

diagnose

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed debugging workflow that can be broad and resource-intensive, but its behavior fits its stated purpose and does not show hidden or malicious actions.

Install this if you want an agent to follow a rigorous debugging process. Expect it to run or create targeted repros, inspect relevant code, and sometimes use parallel exploratory agents on harder bugs; give clear scope if you only want a small fix or explanation.

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
Confidence
93% confidence
Finding
The skill auto-activates on very broad user language like 'broken', 'failing', or 'got slower', including cases where the user did not explicitly request this skill. In an agent framework, this can cause unintended routing and execution of a powerful multi-step debugging workflow, increasing the chance of overreach, unnecessary tool use, and context drift on ordinary conversations.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The 'when to use' section repeats expansive triggers that match common support and debugging language without a crisp invocation boundary. Because the skill also encourages substantial investigation and sub-agent spawning on non-trivial cases, accidental activation can consume resources, expose more code/context than necessary, and lead the agent into acting beyond the user's intended scope.

Static analysis

No suspicious patterns detected.