ClawHub
Back to skill

Security audit

Infra

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only infrastructure guidance skill with no executable code, persistence, hidden data flow, or automatic privileged behavior.

Installers should understand that this skill is broad and may shape responses across infrastructure, cloud, security, and incident-response tasks. It does not itself execute commands or access systems, but users should still review any infrastructure changes the agent proposes before applying them.

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 (2)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
80% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · skill.md (reported line 80)May include surrounding context.

md
**Network security** — what can talk to what — is the second layer. Internal services that should not be reachable from the internet. Databases that should only accept connections from specific application servers. Management interfaces that should only be accessible through a bastion or VPN. The skill reviews network configurations for exposures and helps you close them.

**Secrets management** — how credentials, API keys, and certificates are stored and rotated — is where many breaches originate. Credentials in environment variables. API keys in code repositories. Certificates that expire without warning. The skill helps you implement proper secrets management and identifies existing secrets hygiene problems.

**Vulnerability management** — keeping software patched and dependencies updated — requires a systematic process rather than periodic heroic efforts. The skill helps you build and maintain this process.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description says the skill is for 'managing, designing, and troubleshooting technical infrastructure' and 'helps engineers' across a very wide range of tasks, but it does not define concrete trigger phrases, scope boundaries, or non-applicable cases. For a markdown/manifest file, this breadth creates ambiguous activation conditions and increases the chance of unintended invocation for many common infrastructure-related requests.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.