ClawHub
Back to skill

Security audit

Websearch

Security checks for vulnerabilities and agentic risk

Overview

This web search skill uses disclosed third-party web/search services for its stated purpose and shows no hidden persistence, privilege escalation, or destructive behavior.

Before installing, understand that URLs and search queries may be sent to Jina Reader or Exa. Do not use it with secret tokens in URLs, private internal links, or confidential research terms unless you are comfortable sharing those inputs with those services. Also note that the published artifact appears documentation-only and may not run as described without the missing scripts and package files.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The README instructs users to submit arbitrary URLs to Jina Reader and keyword queries to Exa, but it does not disclose that these inputs are transmitted to third-party services. This creates a privacy and data-handling risk because users may unknowingly send sensitive internal URLs, tokens in query strings, proprietary research topics, or confidential search terms to external providers.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill sends user-supplied URLs to the external Jina Reader service (`https://r.jina.ai/`) for retrieval, but the user-facing description does not clearly warn that requested content is being transmitted to a third party. This creates a privacy and data-handling risk because users may provide internal, sensitive, or proprietary URLs assuming the fetch happens locally, when in fact an external service receives the target URL and may log or process it.

Static analysis

No suspicious patterns detected.