ClawHub
Back to skill

Security audit

Web Fetch Fake-IP Workaround

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed, user-run workaround that patches an older global OpenClaw install for fake-IP web_fetch failures, with clear revert steps.

Install only if you are on an older npm-global OpenClaw version affected by fake-IP web_fetch blocking. Prefer the openclaw.json ssrfPolicy configuration on OpenClaw v2026.4.10 or later. Before applying, run status and inspect, understand that it modifies your global OpenClaw runtime and allows the RFC2544 fake-IP range, then use the documented revert command if the workaround is no longer needed.

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 (2)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding

The skill instructs users to run a patch script that modifies a globally installed OpenClaw component, but the manifest declares no explicit tool scope or permissions. That mismatch reduces transparency and weakens policy enforcement, making it easier for a skill to perform environment-affecting actions without prior declaration or review. In this context, the skill is especially sensitive because it changes network-guard behavior to allow a previously blocked IP range.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

The script's user-facing help text is entirely in Chinese, which imposes a specific language on all users. The file does not indicate that the skill is intended only for a Chinese-speaking or region-specific audience, nor does it offer an alternative language.

Content

No source excerpt is available for this finding.