ClawHub
Back to skill

Security audit

Crisis Communications Playbook

Security checks for vulnerabilities and agentic risk

Overview

This is a simple crisis-communications drafting skill with no code execution, persistence, credential access, or hidden behavior found.

Installers should understand this skill produces draft crisis messaging, not verified legal, regulatory, security, or public-disclosure advice. Before using any generated statement externally, have appropriate legal, security, communications, and business owners verify the facts, obligations, audience, timing, and wording.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
This skill helps generate external-facing crisis messaging for high-stakes scenarios such as data breaches, outages, legal actions, and regulatory investigations, but it provides no warning that outputs may be inaccurate, incomplete, privileged, or legally risky if used without human review. In this context, users may over-trust fast AI-generated statements and publish them directly, creating reputational harm, regulatory exposure, or admissions that worsen the underlying incident.

Static analysis

No suspicious patterns detected.