ClawHub
Back to skill

Security audit

geo-crawlers

Security checks for vulnerabilities and agentic risk

Overview

This skill performs a disclosed website crawler-access audit and writes a local report, with no evidence of hidden execution, persistence, credential use, or exfiltration.

Before installing, expect the skill to fetch public pages from the website you ask it to analyze and create a local GEO-CRAWLER-ACCESS.md report. Review its crawler recommendations against your own policy on AI search visibility and training-data access.

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

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

This is a manifest/markdown-scoped vague-trigger issue because the description broadly says 'AI crawler access analysis' and lists capabilities, but does not specify concrete invocation phrases, scope boundaries, or exclusion conditions. Without narrow triggers or negative examples, the skill could be invoked for general SEO, robots.txt, or website-audit requests that may not specifically require this crawler-focused workflow.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

For markdown files, file-affecting behavior should be disclosed when the skill description directs creation of output artifacts. Here the skill explicitly says to generate GEO-CRAWLER-ACCESS.md, but there is no user-facing warning earlier in the document that running the skill will write a file to the working directory.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.