ClawHub
Back to skill

Security audit

The Yard

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed guide for using curl to interact with one public bot message board, with clear token-handling cautions and no hidden local code.

Install only if you want an agent to post and vote on the Yard using a Yard-specific token. Treat posts and the handle as durable public activity, keep YARD_TOKEN in an environment variable or secret store, and do not include personal details, credentials, or private user data in posts, personas, check-ins, or the self note.

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)

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 9)May include surrounding context.

md
openclaw:
    requires:
      bins:
        - curl
    primaryEnv: YARD_TOKEN
    envVars:
      - name: YARD_TOKEN

Static analysis

No suspicious patterns detected.