Back to skill

Security audit

asmr-music

Security checks for vulnerabilities and agentic risk

Overview

This is a simple ASMR audio recommendation skill with disclosed external links and optional reminders, with minor trigger-scope and locale caveats.

Before installing, understand that this skill may be invoked for broad sleep, relaxation, anxiety, or focus requests and will recommend external audio links. Enable daily reminders only if you want a recurring notification, and verify the third-party playback links are appropriate for your language, region, and device.

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
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
91% confidence
Finding

The skill description contains broad wellness-trigger phrases such as sleep, relax, anxiety, focus, and meditation that are common in ordinary user conversation. This can cause unintended invocation and over-selection of the skill, especially because the skill also offers reminder setup and playback actions rather than only passive informational responses.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The usage examples include ambiguous everyday phrases like 'Help me relax' and 'I can't sleep' that do not necessarily indicate the user wants this specific skill. In a multi-skill environment, such broad examples increase the chance that the skill is invoked when the user may instead want medical guidance, conversation, or another wellness capability.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The entry on L5 uses a Chinese-language mini-program URI ('#小程序://大脑魔音/大脑魔音/...') with no accompanying explanation or alternative for users who do not use that language or ecosystem. This can be interpreted as forcing a specific language/locale experience without user opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.