ClawHub
Back to skill

Security audit

Web fetch Google search

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple Google search helper, and its network use is expected for its stated purpose.

Install only if you want an agent to perform Google-style web searches. Do not use it for secrets, private identifiers, proprietary text, or other sensitive queries unless you are comfortable sending that query to an external search service.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill activation text is overly broad: it says to use the skill whenever information is needed from Google search results, without clear trigger boundaries, exclusions, or approval requirements. Broad activation increases the chance the agent invokes external search in situations involving sensitive user data or where local/non-network sources would be safer, creating unnecessary data exposure and unpredictable behavior.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs execution of a script that performs a Google web fetch, but it does not warn that the action sends user-provided queries to an external service. Without a user-facing notice or consent gate, users may unknowingly expose sensitive prompts, identifiers, or proprietary information to third parties and trigger unintended network activity.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.