ClawHub
Back to skill

Security audit

Code Docs Search by Exa

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Exa-powered documentation search helper, with the main caveat that user queries are sent to a remote MCP service.

Before installing, treat this as a remote search tool: use it for public library, SDK, and documentation questions, and avoid sending secrets, credentials, private source code, internal URLs, customer data, or proprietary prompts in queries.

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 (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs users to connect to a remote MCP server and send free-form queries, but it does not warn that those queries leave the local environment and are transmitted to Exa infrastructure. This can cause accidental disclosure of sensitive code, internal project details, secrets, or proprietary prompts if users treat the tool as local documentation search.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.