ClawHub

IR Playbook Generator

Security checks across malware telemetry and agentic risk

Overview

This is a coherent third-party API skill for generating incident response playbooks, but users should treat submitted organization details as sensitive.

Before using this with real organizational data, verify the API operator, privacy terms, retention/logging practices, and authorization to share incident-response details. Use redacted placeholders for testing, avoid secrets and unnecessary personal contact information, and have security or legal staff review generated procedures before operational use.

SkillSpector

By NVIDIA
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 (2)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill explicitly describes ingesting and generating organization-specific incident response content that can include sensitive operational details, security posture information, legal obligations, and emergency contact data, but it provides no privacy, minimization, or data-handling warning. In a security-focused workflow, users may submit highly sensitive incident and infrastructure information to an external service without understanding the exposure, increasing confidentiality and compliance risk.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The sample request encourages transmission of detailed organizational assessment data to an external API, including critical systems, threats, compliance frameworks, session identifiers, and user identifiers, without any caution about sensitivity or third-party disclosure. Because this skill is for incident response planning, users are likely to provide especially valuable security metadata that could aid attackers or create regulatory/privacy issues if mishandled.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal