ClawHub
Back to skill

Security audit

Dead Link Scanner

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward dead-link checker, but users should know it contacts links found in selected local files or crawled pages.

Install only if you are comfortable with the skill making outbound requests to links it finds. Use it on documentation and sites you intend to audit, prefer --internal-only for website scans when appropriate, and avoid scanning private files that contain confidential internal URLs or secret-bearing query strings.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding

The skill invokes a Python script that reads local files and makes outbound network requests, but the manifest does not declare any explicit tool scope such as permissions or allowed-tools. This creates an authorization gap: an agent or platform may execute file and network operations without clear, reviewable constraints, increasing the risk of unintended data access, SSRF-style internal probing, or misuse beyond the stated dead-link-scanning purpose.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file-scanning mode extracts URLs from local markdown/HTML content and automatically issues outbound HTTP requests to every discovered http(s) link. This can leak sensitive internal URLs embedded in private files, trigger unexpected access to internal-only endpoints if the tool runs inside a trusted network, and surprise users because merely scanning a local file causes network activity.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.