ClawHub
Back to skill

Security audit

Incident Commander

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward incident-response guide that does not request execution, credentials, persistence, or broad system access.

Installers should treat this as an incident-response playbook and template helper. It may help draft sensitive stakeholder communications, so users should review generated updates for accuracy before sending, but the artifact itself does not introduce privileged or hidden behavior.

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
Confidence
91% confidence
Finding
The usage example "We have a production incident — help me manage it" includes the broad phrase "help me manage it," which is ambiguous and could match ordinary conversation outside a narrowly defined invocation pattern. The file does not provide exclusion conditions or explicit trigger constraints to clarify when this skill should activate versus when it should not.

Static analysis

No suspicious patterns detected.