ClawHub
Back to skill

Security audit

risk-manager

Security checks for vulnerabilities and agentic risk

Overview

This skill is a plain risk-management guidance prompt with broad but disclosed enterprise risk and compliance scope, and no code, install hooks, persistence, or hidden data handling.

Use this skill for risk assessment, compliance gap analysis, and control-planning work. Require explicit confirmation before letting an agent make real business, financial, policy, reporting, or regulatory claims based on its recommendations.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill metadata describes a very broad 'expert risk manager' capability without clear invocation boundaries, permitted actions, or scoped triggers. In an agent system, this can cause over-selection of the skill for loosely related prompts and may lead it to access context, generate compliance assertions, or drive workflow actions beyond the user's actual intent.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.