ClawHub
Back to skill

Security audit

FortiGate Hardening

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent FortiGate configuration generator, but users should review generated firewall changes carefully before applying them.

Install only if you are comfortable sending FortiGate hardening options and request metadata to the listed third-party API. Treat generated firewall configurations as drafts: review diffs, test outside production, keep rollback and out-of-band management access, and avoid sending unnecessary real user identifiers.

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 (5)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill presents itself as producing production-ready FortiGate hardening configurations but does not warn that applying generated firewall changes can materially affect routing, management access, or service availability. In a firewall-hardening context, omission of a review/validation warning is risky because users may treat output as safe-to-apply automation and unintentionally lock themselves out or disrupt business traffic.

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 76)May include surrounding context.

} } }, "download_url": "https://api.mkkpro.com/hardening/fortigate/cfg_xyz789abc123" }

text

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 178)May include surrounding context.

} } }, "download_url": "https://api.mkkpro.com/hardening/fortigate/cfg_xyz789abc123" }

text

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The example request includes sessionId, userId, and timestamp values without any note that these identifiers may be sensitive operational metadata and should not be shared unnecessarily. In an API skill, such examples can normalize sending persistent identifiers to third-party services without clarifying retention, minimization, or masking expectations.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

This is a manifest-format file, so vague-trigger review applies. The description 'Generate FortiGate security hardening configuration files' states the capability but gives no specificity about when this skill should be invoked, acceptable contexts, or exclusions, which can make activation criteria overly broad in agent routing contexts.

Content

No source excerpt is available for this finding.