ClawHub
Back to skill

Security audit

ClawHub Ingest Runbook

Security checks for vulnerabilities and agentic risk

Overview

This is a transparent runbook for publishing a specific skill package to ClawHub; the main thing to watch is that publishing shares the package contents externally.

Before installing or following this runbook, confirm the folder you publish contains only material intended for ClawHub and approved for external visibility. Run the documented dry-run first, verify the slug and account identity, and only then perform the real publish.

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 (3)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The runbook explicitly instructs users to publish content to a remote resource center, making local workspace material discoverable and installable, but it does not clearly warn that this transmits content outside the local environment and may expose proprietary or sensitive data. In a workflow handoff artifact that is intended as direct input to another tool, that omission increases the chance that publication is treated as a routine step rather than a consented external disclosure.

Natural-Language Policy Violations

Low
Confidence
92% confidence
Finding
This markdown file contains user-facing natural language exclusively in Chinese, but does not state that the skill is Chinese-only or offer an alternative language option. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern.

Natural-Language Policy Violations

Low
Confidence
95% confidence
Finding
The document's operational instructions and labels are presented in Chinese throughout, but there is no statement that the skill is China-region-specific, Chinese-only by design, or that the user can opt into this locale. Under the stated policy, forcing a specific language without opt-in is a natural-language policy concern.

Static analysis

No suspicious patterns detected.