ClawHub
Back to skill

Security audit

audit system

Security checks for vulnerabilities and agentic risk

Overview

This instruction-only audit skill is broad in when it may activate, but it is coherent and does not request special access or persistent changes.

Install this if you want a reusable structured audit format. Be aware it may be selected for a wide range of review or debugging requests, so provide only the code, logs, prompts, or workflow details you intend the agent to analyze.

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
95% confidence
Finding

The skill description includes very broad activation triggers such as 'something is not working as expected,' 'user asks for review or feedback,' and 'before deploying or shipping,' which are common situations across many conversations. This can cause unintended invocation, routing users into this skill when a narrower or safer skill would be more appropriate, increasing the chance of over-collection of context, unnecessary audits, or workflow confusion.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.