ClawHub
Back to skill

Security audit

Writing

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only writing style skill with broad but disclosed copyediting guidance and no hidden privileged behavior.

Install this if you want strong, opinionated prose editing rules. Be aware it may activate for many writing tasks, and drafts given to the agent may also be shared with a copyediting subagent if your runtime supports that workflow.

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
90% confidence
Finding

The manifest says to use the skill when 'writing or editing prose humans will read' and that it triggers on broad conditions like 'clarity concerns' or 'vague language.' Those conditions are common across many everyday prompts and the file does not provide specific trigger phrases, boundaries, or negative examples to constrain invocation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.