ClawHub
Back to skill

Security audit

Crawl By Desearch

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Desearch webpage-crawl wrapper with disclosed API-key and network use, and no hidden persistence or destructive behavior.

Before installing, only use this with URLs you are allowed to crawl and understand that your Desearch API key will be used for requests to Desearch, which may see the target URL and crawl results. Consider account cost limits and avoid submitting sensitive internal URLs unless you trust the service for that data.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
84% confidence
Finding

The skill requires environment access for an API key and performs arbitrary network requests to user-supplied URLs, but it does not declare any explicit tool scope such as permissions or allowed-tools. That omission weakens policy enforcement and reviewability: an agent may invoke network and secret-backed behavior without clear, least-privilege constraints, increasing the risk of SSRF-style access to internal resources or unintended use of credentials.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.