ClawHub
Back to skill

Security audit

Draft

Security checks for vulnerabilities and agentic risk

Overview

This skill is a broad but straightforward first-draft writing helper with no executable code, persistence, credential use, or data-moving behavior.

Install this if you want a general drafting helper. Be aware it may activate for many writing-related prompts, so review outputs carefully for tone, accuracy, and sensitive details before sending or publishing them.

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’s trigger criteria are extremely broad and map to common, everyday writing requests, making it likely to activate in many situations beyond a narrowly scoped use case. Over-broad activation can cause inappropriate routing, shadow more suitable skills, and increase the chance that sensitive or context-specific user tasks are handled by a generic drafting workflow without sufficient safeguards or user confirmation.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The skill allows activation based on ambiguous contextual cues such as rough drafting intent without defining clear disambiguation rules. This can lead to accidental invocation on borderline requests, reducing predictability and potentially interfering with safer or more specialized handling paths.

Static analysis

No suspicious patterns detected.