ClawHub
Back to skill

Security audit

Enterprise Risk Management Engine

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent enterprise risk management guide with templates and does not show hidden execution, data access, persistence, or credential handling.

Before installing, treat this as a business risk analysis aid, not a substitute for qualified legal, compliance, security, or financial advice. Avoid sharing unnecessary confidential business data, and review any generated risk reports before using them with executives, regulators, customers, or staff.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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 243)May include surrounding context.

md
| Velocity | Timeframe | Required Readiness |
|----------|-----------|-------------------|
| **Immediate** | No warning, instant impact | Pre-positioned response plan, tested quarterly |
| **Days** | 1-7 days from trigger to impact | Response plan, decision authority pre-delegated |
| **Weeks** | 1-4 weeks lead time | Monitoring in place, escalation path defined |
| **Months** | 1-6 months visibility | Regular tracking, proactive mitigation |

Vague Triggers

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The trigger phrase "Assess risk for [situation]" is relatively broad and could overlap with ordinary conversation about evaluating a situation, without clear constraints on when this skill should activate versus when general advice is intended. The file lists example commands, but it does not provide exclusion conditions or negative examples to narrow ambiguous invocation scope.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.