ClawHub
Back to skill

Security audit

Caring

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only quality review skill with broad activation language, but it does not request sensitive access or perform hidden actions.

Install this if you want an opinionated final-quality review style. Be aware it may activate for generic requests like reviewing or checking work, so use a more specific skill or instruction when you need a domain-specific review instead.

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)

Vague Triggers

High
Confidence
97% confidence
Finding
The skill advertises very broad trigger phrases such as 'review this', 'check my work', and 'quality review', which are common in ordinary conversation and can cause the skill to activate in many unrelated contexts. This overmatching can unintentionally route diverse user requests through the skill, influencing outputs in situations where a narrow quality-review persona was not intended and increasing the chance of prompt/skill interference.

Vague Triggers

Medium
Confidence
96% confidence
Finding
The skill advertises very broad trigger phrases like "review this," "check my work," and "quality review," which can match a large share of ordinary user requests and cause the skill to activate outside its narrow intended use. Overbroad activation is dangerous because it can override or derail more appropriate task-specific skills and steer the agent into a generic review workflow that may not fit the user’s intent.

Static analysis

No suspicious patterns detected.