ClawHub
Back to skill

Security audit

Network Security Audit

Security checks for vulnerabilities and agentic risk

Overview

This skill appears purpose-built for network security audits, but it sends highly sensitive security posture details to an external API without enough disclosure about data handling or user control.

Review this before installing if your audit notes may include internal hostnames, IP addresses, vulnerabilities, credentials, firewall rules, or compliance findings. Use only sanitized data unless you trust the API operator and have approval to transmit security assessment details to that external service.

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
95% confidence
Finding

The skill solicits detailed network security assessment data, including weaknesses, control gaps, and audit notes, and sends it to a third-party remote API without any explicit warning about data sensitivity, external transmission, retention, or trust boundaries. This is dangerous because users may unknowingly disclose confidential security posture information that could materially aid an attacker or create compliance/privacy issues if the vendor stores, logs, or mishandles the data.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
88% confidence
Finding

The skill references and relies on an external API endpoint, which means security audit content leaves the local trust boundary and is transmitted to infrastructure outside the user's direct control. In the context of a network security audit tool, the transmitted content is especially sensitive because it can include detailed descriptions of missing controls and defensive weaknesses, making the external transmission materially riskier than for ordinary business data.

Content

Scanner excerpt · SKILL.md (reported line 228)May include surrounding context.

md
## References

- **Kong Route:** https://api.mkkpro.com/security/network-security-audit
- **API Docs:** https://api.mkkpro.com:8119/docs

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The audit endpoint is exposed as a broadly callable action with no indication of trigger restrictions, caller scope, or other invocation constraints in the API description. In an agent skill context, this can cause the skill to be invoked too eagerly on loosely related prompts, leading to unnecessary transmission of potentially sensitive security assessment data and unintended external actions.

Content

No source excerpt is available for this finding.