ClawHub
Back to skill

Security audit

IPO Model

Security checks for vulnerabilities and agentic risk

Overview

This skill is a broad task-structuring method with no bundled executable code, persistence, credential handling, or hidden data flows.

Install this only if you want a general IPO-style planning framework. For tasks that modify files, call external services, or use MCPs, keep normal confirmations and scoped permissions in place because the skill itself does not define extra safety gates.

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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill instructs the agent to escalate from analysis into generating commands, scripts, and tool/skill/MCP invocations, including file-affecting workflows, but it does not require user confirmation, safety checks, or impact disclosure before taking system-affecting actions. That omission can enable unsafe execution patterns where the agent moves from abstract planning to real-world modification without adequate guardrails.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly claims it is suitable for 'all types of tasks,' which makes its activation boundary effectively unbounded. In an agent setting, such universal framing increases the chance the skill will be invoked in inappropriate, higher-risk contexts and may cause the model to over-apply its workflow to actions involving sensitive systems or destructive operations.

Content

No source excerpt is available for this finding.