Back to skill

Security audit

Voice Broadcast

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a disclosed voice-broadcast helper, but it can override mute for undefined urgent content and send replies as Feishu audio despite a silence preference.

Review this before installing if you use Feishu in shared, workplace, or sensitive environments. The core voice-broadcast behavior is coherent, but the skill should remove or separately require opt-in for any rule that speaks content while muted.

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
Findings (1)

T01 · Skill Instruction Hijacking

Warning
Location
SKILL.md:54
Finding

Mute Preference Bypass for Urgent Content

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, line 54
Vulnerability Type: User safety and privacy preference override
Risk Level: Medium

Vulnerable Code

markdown
- 危急内容(如急诊处理、危急值)强制播报,忽略静音

English translation:

text
Urgent content, such as emergency handling or critical values, must be broadcast, ignoring mute.

Technical Analysis

The skill explicitly directs the agent to disregard the active mute state when content is classified as urgent. This conflicts with the documented behavior of muted=true, under which voice output should be skipped.

Because the instruction changes the agent's behavior and overrides a user-controlled safety constraint, the best matching classification is T01: Skill Instruction Hijacking. The bypass does not require system privilege escalation or arbitrary code execution; it is triggered through the skill's own instruction-processing and TTS workflow.

Classification of content as urgent is not defined by a deterministic or user-approved policy. Consequently, content identified as an emergency or critical value could be converted to speech and sent through the Feishu voice channel despite an explicit request for silence.

Attack Path

  1. The user enables automatic voice broadcasting.
  2. The user issues the mute command, causing muted=true to be stored.
  3. A subsequent response contains medical, emergency, or other content that the agent classifies as urgent.
  4. The line 54 instruction takes precedence over the mute state.
  5. The agent invokes the TTS tool with the response content.
  6. The resulting audio is sent through Feishu and may play in the user's environment despite the active mute preference.

Impact Assessment

The issue can cause unauthorized audible disclosure of response content in shared, public, workplace, or otherwise sensitive environments. Medical and emergency-related content may itself be particularly sensitive.

...[truncated 322 chars]

Remediation
View remediation

Remediation Suggestions

  • Make muted=true an unconditional prohibition on TTS generation and voice delivery.
  • Remove the instruction that urgent content must bypass mute.
  • While muted, deliver urgent information as text and clearly mark it as urgent without producing audio.
  • If audible escalation is desired, require explicit, informed user opt-in through a separate setting such as allow_urgent_override.
  • Request confirmation before enabling any urgent-audio override and allow the user to revoke it at any time.
  • Define deterministic precedence rules in which privacy controls override automatic broadcasting:
    1. If muted, do not invoke TTS.
    2. If not muted and automatic broadcasting is enabled, invoke TTS.
    3. If automatic broadcasting is disabled, invoke TTS only after an explicit read-aloud request.
  • Add tests verifying that emergency keywords, medical information, and critical-value content cannot trigger TTS while mute is active.
  • Avoid sending response text to the TTS tool when muted, rather than merely suppressing playback after audio generation.
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill routes assistant reply content through TTS and sends audio via Feishu, but it does not clearly warn users that their content will be transformed and transmitted through an external audio/message channel. This creates a privacy and consent risk, especially if replies contain sensitive personal, financial, medical, or workplace information and auto-broadcast is enabled.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The activation model is defined entirely through specific Chinese phrases such as "朗读", "开启语音播报", and "静音", with no indication that users may choose another language or locale. This creates a language/locale constraint in the natural-language interface without documented opt-in or justification.

Content

No source excerpt is available for this finding.