ClawHub
Back to skill

Security audit

Geo Template Library

Security checks for vulnerabilities and agentic risk

Overview

This is a benign content-template skill; its broad routing may make it activate too often, but it does not show hidden, persistent, credential, network, or destructive behavior.

Install this if you want reusable GEO or AI-citation-oriented content templates. Be aware it may activate on some generic template requests, so users may need to specify when they want a non-GEO template or one-off copy 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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (3)

Hidden Instructions

High
Category
Prompt Injection
Content
This file provides **ready-to-copy markdown skeletons** for the main template families described in
`templates-catalog.md`. Use these as concrete starting points when generating templates.

Comments marked with `<!-- GEO: ... -->` highlight sections that are especially important for
AI citation.

---
Confidence
70% confidence
Finding
Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The skill metadata and description instruct invocation for very generic requests like 'a template' or 'reusable structure,' which can cause the skill to activate outside its intended GEO-specific scope. Over-broad routing can override more appropriate skills, produce irrelevant outputs, and increase the chance that downstream content-generation behavior is applied in contexts the user did not intend.

Vague Triggers

Medium
Confidence
97% confidence
Finding
The instruction to 'not restrict triggering' and instead infer broad intent makes activation boundaries ambiguous and encourages speculative invocation. In multi-skill systems, this can lead to unintended skill selection, response hijacking by a loosely related skill, and reduced predictability or safety of orchestration.

Static analysis

No suspicious patterns detected.