ClawHub
Back to skill

Security audit

It Risk Assessment Tool

Security checks for vulnerabilities and agentic risk

Overview

This skill openly works by sending detailed IT security posture answers to ToolWeb's external API, but it makes that transmission mandatory without a clear consent checkpoint.

Review this before installing if the assessment may include confidential company security details. Use it only if your organization approves sending that information to ToolWeb, understands the billing/API-key implications, and is comfortable with the provider's retention and handling practices.

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
Findings (1)

T01 · Skill Instruction Hijacking

Error
Location
SKILL.md:44
Finding

Mandatory Transmission of Sensitive Security-Posture Data to a Commercial External API

Content
View full analysis
", "infra_firewall": "", "infra_patching": "", "data_classification": "", "data_encryption": "", "data_backup": "", "access_mfa": "", "access_pam": "", "access_review": "", "comp_policies": "", "comp_regulatory": "", "comp_training": "", "ir_plan": "", "ir_monitoring": "", "ir_threat": "", "vendor_assessment": "", "vendor_contracts": "", "vendor_monitoring": "", "sessionId": "" }' ``` Generate a unique `sessionId` (e.g., UUID or timestamp-based). ``` The prescribed output also requires third-party branding: ```markdown 📎 Full report powered by ToolWeb.in ...[truncated 3526 chars]
Remediation
View remediation

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 (2)

External Transmission

Medium
Category
Data Exfiltration
Confidence
90% confidence
Finding

This skill is designed to exfiltrate user-provided assessment data to an external network endpoint via curl, which is expected behavior for the integration but still represents a real data-transfer risk. In this context, the transmitted content is especially sensitive because it includes detailed security control maturity, incident response readiness, access-control weaknesses, and vendor-risk information that could aid attackers or create compliance/privacy issues if mishandled.

Content

Scanner excerpt · SKILL.md (reported line 13)May include surrounding context.

md
env:
        - TOOLWEB_API_KEY
      bins:
        - curl
    primaryEnv: TOOLWEB_API_KEY
    os:
      - linux

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs the agent to collect detailed organizational security posture information across 18 controls and send it to an external ToolWeb API, but it does not clearly warn the user that this sensitive operational data will leave the local environment. This creates a confidentiality and informed-consent problem because users may disclose internal security weaknesses, compliance gaps, and vendor-risk details without realizing they are being transmitted to a third party.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.