ClawHub
Back to skill

Security audit

RedHat Debugger

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward debugging workflow skill with a malformed trigger metadata field, but no evidence of hidden, persistent, destructive, or data-exfiltrating behavior.

Before installing, be aware that the activation trigger metadata may be unreliable, so the skill could be invoked less predictably than intended; otherwise it appears limited to ordinary debugging guidance, and users should avoid providing secrets in logs or environment details.

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
94% confidence
Finding

The trigger field is effectively undefined/ambiguous (System.Object[]) and provides no concrete activation phrases, scope, or constraints. In an agent skill, this can cause overly broad or unpredictable invocation, increasing the chance the debugging skill is selected in unintended contexts and processes sensitive or unrelated user inputs.

Content

No source excerpt is available for this finding.