Back to skill

Security audit

ASMR Sleep Sound Generator | ASMR助眠音生成器

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent for a browser-based ASMR generator, but it asks users to store an LLM API key in browser localStorage, which deserves review before installation.

Review this skill before installing if you plan to use the LLM feature. Use a restricted, low-quota, revocable API key, avoid entering a primary provider key, and clear browser storage when done. If running the local server, bind it to localhost only, for example with --bind 127.0.0.1, and do not serve directories containing secrets.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (2)

T09 · Insecure Skill Coding Practices

Error
Location
SKILL.md:37
Finding

Persistent plaintext storage of LLM API credentials in browser localStorage

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:46
Finding

Documented development server command exposes the served directory on network interfaces

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The skill name, description, and usage content are presented bilingually in Chinese and English, but the natural-language control feature does not state that users may choose their preferred language or locale. Because the policy requires avoiding forced language or locale behavior without opt-in or justification, this is a mild natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The natural-language content in the changelog is presented bilingually in Chinese and English across multiple entries, but the file does not state whether language selection is optional or user-configurable. Under the language/locale policy rule, forcing or assuming a language without opt-in can be a policy concern, even in descriptive metadata.

Content

No source excerpt is available for this finding.