Crisis Communications Playbook

• Outcome: Pass
• Latest audit: May 28, 2026 at 11:35 AM UTC
• Version:
  1.0.0

Overview

This appears to be a documentation-only crisis communications drafting skill, with no evidence of code execution, data access, persistence, or exfiltration.

Install only if you understand that crisis messages generated by the skill are drafts. For data breaches, regulatory investigations, financial restatements, layoffs, or other sensitive incidents, have legal, compliance, security, executive, and communications stakeholders review and approve any output before sending it internally or externally.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The README presents AI-generated crisis communications for sensitive scenarios such as data breaches, regulatory investigations, and financial restatements as fast, ready-to-use outputs without any clear requirement for legal, compliance, PR, or incident-response review. In these contexts, inaccurate or premature statements can create regulatory exposure, misrepresentation risk, evidence preservation issues, and material reputational harm, especially during the first hours of an incident.

VirusTotal

64/64 vendors flagged this skill as clean.