ClawHub
Back to skill

Security audit

Daily Draw For Lucky

Security checks for vulnerabilities and agentic risk

Overview

This is a simple bilingual fortune-draw skill with no code, dependencies, credential access, network use, or persistence behavior in the inspected artifact.

Before installing, consider whether the broad "draw" trigger may be annoying in normal use. Prefer invoking it with "/draw" or a more specific Chinese fortune-draw phrase when possible.

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
95% confidence
Finding
The trigger phrase "draw" is extremely generic and can easily appear in normal conversation, such as requests to draw a picture or discuss drawing. In an agent environment, this increases the chance of accidental skill activation, causing unintended oracle responses and potential interference with unrelated user tasks.

Natural-Language Policy Violations

Low
Confidence
81% confidence
Finding
The file consistently mixes English and Chinese in the title, usage, and content, but does not state how language is selected or whether the user can choose a preferred locale. This can conflict with language/locale policies when a skill imposes or assumes a language presentation without explicit user opt-in.

Static analysis

No suspicious patterns detected.