ClawHub
Back to skill

Security audit

web-search-skill

Security checks for vulnerabilities and agentic risk

Overview

This skill only gives web-search and page-fetching instructions for current information lookup, with no executable code, persistence, or hidden local access.

Install only if you want the agent to perform live web searches and fetch web pages. For legal, finance, personal, or security-sensitive questions, keep queries explicit and review cited sources before relying on the answer.

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
88% confidence
Finding

The skill metadata and description define broad web-search capabilities but do not specify clear activation boundaries, allowed query types, or concrete trigger conditions. This can cause overbroad invocation in unrelated contexts, increasing the chance that the agent performs unintended external retrieval, including for sensitive or high-risk domains such as finance or legal topics without sufficient guardrails.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The natural-language instructions and description are presented in Korean, which may implicitly force a specific language experience. There is no statement offering multilingual support, user language selection, or justification for a Korean-only locale.

Content

No source excerpt is available for this finding.