ClawHub
Back to skill

Security audit

Search Synthesis Expert

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed web research helper that uses browser search and source synthesis, with no bundled code or persistence.

Before installing, understand that this skill is meant to browse the web on your behalf. Do not include passwords, secrets, private customer data, or sensitive internal project names in prompts unless you are comfortable with related search terms or page requests reaching external sites. For locale-sensitive research, ask it to use the region and language you prefer.

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
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly performs automated web searches and page visits using Playwright, which will transmit user-provided queries and possibly derived sub-queries to third-party search engines and websites. Because the documentation does not warn users about this external data disclosure or browsing automation, users may unknowingly expose sensitive research topics, internal terms, or proprietary information.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The example workflow hard-codes navigation to google.com, which commonly defaults to an English/global locale, and the skill does not mention respecting the user's preferred language or locale for search. Because the documentation frames this as the standard search flow without offering a locale choice, it may conflict with language/locale policy expectations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.