ClawHub
Back to skill

Security audit

音乐创作助手

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed markdown-only music creation workflow that guides song, lyric, arrangement, and HappyShrimp prompt generation without hidden execution or sensitive access.

Review the HappyShrimp guidance before using credits or creating an account, and specify your preferred lyric/prompt language if you do not want Chinese defaults. The skill appears safe to install from a security perspective.

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill description uses very broad trigger phrases such as '写歌曲', '创作音乐', and '作曲', which overlap with common user intents and can cause the skill to be invoked when the user did not explicitly ask for this specific workflow. Unintended invocation can steer users into a rigid multi-step flow, expose them to external service guidance, and override more appropriate domain-specific handling by other skills.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill states a default preference to prioritize Chinese for style descriptions without first checking the user's language preference. While low severity, this can cause the system to disregard user autonomy or produce outputs in an unintended language, especially for multilingual or English-only requests.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

SQP-3 applies to all file types and includes language or locale policy violations. This markdown reference consistently uses Chinese instructions and descriptions, but does not indicate that Chinese is optional, user-selected, or required for a region-specific use case.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.