ClawHub
Back to skill

Security audit

Web Crawling Html API

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Just Serp API connector that sends a user-provided URL to a documented web-crawling endpoint and returns HTML data.

Install only if you are comfortable sending requested URLs to Just Serp API under your API key. Do not use it for localhost, internal systems, secret-bearing URLs, or pages whose contents or addresses should not be shared with that provider.

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

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill clearly enables outbound network access to a third-party API via the Node helper, but it does not declare any explicit tool scope such as allowed-tools or permissions. This creates a governance gap: callers or reviewers cannot easily constrain or audit the skill's network behavior, and a modified helper or future extension could make unintended external requests under the same undeclared capability.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill forwards a user-provided target URL together with the caller's API key to a third-party service, but the code provides no disclosure, confirmation, or guardrails about this data transfer. In an agent/tooling context, this can cause unintended exfiltration of sensitive internal URLs, query tokens, or reconnaissance targets to an external provider, especially if the agent is prompted to fetch attacker-supplied or internal-only resources.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.