ClawHub
Back to skill

Security audit

AgentRepoRouter

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed install notice for a repo-routing skill, with no bundled executable code, but users should review the external installer because it changes local agent-host routing configuration.

Before installing, review the linked upstream repository and installer because the reviewed ClawHub package does not contain the runtime implementation. Confirm the exact agent hosts, CLI backends, and repository mapping file it will create or link, especially if you use multiple coding agents.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

Line L24 states that the setup 'selects an English or Chinese runtime skill,' which is a natural-language locale constraint. The file does not clarify that this is an optional user-selected preference or a justified region-specific limitation, so it may violate the language/locale policy requirement.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.