ClawHub
Back to skill

Security audit

sleep-wakeup advisor

Security checks for vulnerabilities and agentic risk

Overview

This skill only provides sleep-cycle wake-up time suggestions and does not request access to files, credentials, tools, or persistent system changes.

Before installing, users should know this skill is oriented toward Chinese-language wake-up advice and China holiday assumptions; it appears low-risk because it only formats sleep-cycle recommendations and does not gain access to local data or execute code.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (2)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The invocation trigger is broad enough to activate on general sleep-related queries, which can cause the skill to respond outside its intended narrow context. This is not a direct security exploit, but it can lead to incorrect routing, reduced user control, and unintended behavior if it overrides more appropriate skills or broader assistant logic.

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
The response template mandates Chinese output strings such as "最推荐" and "备选," and the trigger also centers on a Chinese phrase. There is no indication that the user may choose another language or that the skill is intentionally restricted to Chinese-speaking users for a documented reason.

Static analysis

No suspicious patterns detected.