ClawHub
Back to skill

Security audit

Relay Knowledge CLI

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed local CLI workflow for repository knowledge indexing and map maintenance, with sensitive actions scoped to explicit repository, service, or feedback-publication workflows.

Before installing, confirm you want agents to use relay-knowledge for local repository indexing and map updates. Keep scope to repositories you authorize, prefer verified published installs, and enable feedback auto-submit or local service persistence only when you intentionally want those behaviors.

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

Medium
Category
Not specified by scanner
Confidence
80% confidence
Finding

The description embeds several Chinese-only usage cues such as "目录化知识管理" and "查询类型" as part of when to use the skill, but the document does not state that the skill is region-specific or give users a language/locale option. That can create a language policy issue by implicitly privileging one locale without opt-in or justification.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.