ClawHub
Back to skill

Security audit

Groundapi Web Researcher

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed web-research helper that sends research queries to GroundAPI, with no hidden code, persistence, or destructive behavior found.

Install this if you want GroundAPI-powered web research and are comfortable sending search topics, selected URLs, and trend queries to that service. Keep the GroundAPI key scoped and private, and be aware the broad trigger wording may invoke the skill for ordinary search or summary requests.

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
  • 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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The activation examples are broad enough to match many ordinary user requests such as 'search this', 'summarize this topic', or 'compare A and B', which can cause the skill to trigger unintentionally. In a tool-enabled research skill, unintended invocation can lead to unnecessary external searches, scraping, and data flow to third-party services, increasing privacy, cost, and prompt-routing risk.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The trending-topic trigger ('现在什么最火', '今天有什么热点') is ambiguous and may activate on casual conversation or general curiosity without clear consent to use external tools. Because the skill then queries trending and bulletin services and may pivot to recent searches automatically, it can expand scope beyond the user's precise request and send data to remote services unnecessarily.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.