ClawHub
Back to skill

Security audit

Active Directory Hardening

Security checks for vulnerabilities and agentic risk

Overview

This skill appears purpose-built for AD hardening, but it sends security configuration requests to an external API and returns deployment scripts without enough safety or data-handling disclosure.

Review this skill before installing in an enterprise environment. Treat generated AD scripts as advisory output only: test them in a non-production domain, run change control, verify service-account and legacy compatibility, and establish rollback steps. Do not send real user identifiers or detailed environment data to the external API unless the provider's privacy, retention, and security practices meet your organization's requirements.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill advertises deployment-ready AD hardening configurations and scripts but does not warn that applying them can alter authentication, authorization, Kerberos, password, and network access settings in ways that may disrupt production environments or lock out users and administrators. In the context of Active Directory, even well-intended hardening changes are high-sensitivity operations, so omission of a review/change-control warning increases the risk of unsafe deployment.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
71% confidence
Finding

The skill directs users to an external API endpoint, which means request contents and any generated configuration data may be transmitted outside the local environment to a third-party service. In an enterprise Active Directory hardening context, this is sensitive because configuration intent, environment details, user identifiers, and deployment artifacts may reveal security posture or administrative activity.

Content

Scanner excerpt · SKILL.md (reported line 164)May include surrounding context.

md
# References

- **Kong Route:** https://api.mkkpro.com/hardening/active-directory
- **API Documentation:** https://api.mkkpro.com:8127/docs

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

This OpenAPI manifest defines a POST request body containing sessionId, userId, and timestamp, which indicates the skill transmits user/session metadata over the network. The spec does not include any warning or disclosure in the endpoint or schema descriptions about collecting or sending these identifiers, creating a missing-warning issue for a networked operation involving potentially sensitive data.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The request and response examples include sessionId, userId, and audit logging fields, but the skill provides no notice about collection, retention, sharing, or sensitivity of that metadata. This can expose organizations to privacy, compliance, and traceability risks, especially if identifiers map to real users or are forwarded to third-party API infrastructure.

Content

No source excerpt is available for this finding.