ClawHub
Back to skill

Security audit

Writing Assistant

Security checks for vulnerabilities and agentic risk

Overview

This is a simple writing-assistant routing skill with no executable code, persistence, credential handling, or hidden behavior found.

Before installing, confirm that the MCP writing tools available in your environment are ones you trust, since the skill delegates to unspecified appropriate tools. The skill itself appears low risk and limited to writing assistance.

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
89% confidence
Finding

The skill description and instructions are broadly scoped to 'analyze the writing task' and route work to tools without defining clear activation boundaries, permitted inputs, or constraints on tool usage. This increases the chance the skill will engage on unintended prompts or process adversarial content, which can lead to prompt injection exposure, misrouting of tasks, or unsafe handling of untrusted references.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.