ClawHub
Back to skill

Security audit

War Room Debug

Security checks for vulnerabilities and agentic risk

Overview

This is a simple incident-response workflow skill with no executable code, though its broad trigger phrases may activate it more often than intended.

Install this only if you want the agent to switch into a structured incident-response workflow for urgent problems. Be aware that ordinary phrases like "critical issue" or "emergency fix" may trigger it; confirm the desired workflow before letting it coordinate fixes or create shared state notes.

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
95% confidence
Finding

The trigger list includes broad operational phrases like "critical issue," "emergency fix," and "all hands on deck" that are likely to appear in normal conversation. This can cause unintended activation of the skill during routine troubleshooting, which is especially risky because the skill changes coordination behavior and prioritization under crisis conditions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.