ClawHub
Back to skill

Security audit

Skill Idea Generator

Security checks for vulnerabilities and agentic risk

Overview

This Markdown-only skill gives ideas and templates for making ClawHub skills, with no executable behavior or hidden access.

Installing this skill is low risk from the inspected artifact. Treat its market-performance claims as unsourced guidance, and if you use its template to publish another skill, replace broad trigger placeholders with narrow, task-specific activation wording and clear scope boundaries.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Credential Access

High
Category
Privilege Escalation
Content
9. **API Testing Toolkit** - curl templates, test cases, auth helpers
10. **Git Commit Message Generator** - Conventional commits, semantic versioning
11. **Docker Compose Generator** - Templates for common stacks
12. **ENV File Manager** - Manage .env files across environments
13. **Regex Pattern Library** - Common regex patterns with examples
14. **CSV to Markdown Converter** - Quick table conversion
15. **Code Review Checklist** - PR review templates per language
Confidence
60% confidence
Finding
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The template explicitly instructs authors to use generic 'trigger phrases' without constraining scope, which can lead to overly broad skill activation conditions. In an agent ecosystem, broad triggers increase the chance a skill is invoked in unintended contexts, causing prompt hijacking of unrelated tasks or unsafe execution pathways.

Static analysis

No suspicious patterns detected.