ClawHub
Back to skill

Security audit

pfSense Hardening

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed hosted API wrapper for generating pfSense hardening configurations, with no local execution, persistence, or hidden behavior in the inspected artifacts.

Before installing, treat the generated configuration as advisory output: review and test it in a non-production environment, keep a backup and recovery path, and do not send secrets or sensitive firewall details to the hosted API unless you trust the provider.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill generates firewall hardening configurations that can directly change access controls, TLS settings, and logging behavior, yet it provides no warning that applying generated output without review may disrupt connectivity or lock out administrators. In this context, omission of an operational safety warning increases the chance of self-inflicted denial of service or administrative lockout, especially for users treating the output as automatically safe because the tool is marketed as security-focused.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 126)May include surrounding context.

md
## References

- Kong Route: https://api.mkkpro.com/hardening/pfsense
- API Docs: https://api.mkkpro.com:8131/docs

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The POST operation summary is simply "Generate," which is too vague to clearly communicate the action, inputs, and security-sensitive output of this endpoint. In an agent/tooling context, ambiguous operation descriptions increase the chance that an LLM or user invokes the endpoint in the wrong context or with unsafe assumptions, potentially causing unintended generation or application of firewall-hardening configurations.

Content

No source excerpt is available for this finding.