Back to skill

Security audit

Beep · 小喇叭

Security checks for vulnerabilities and agentic risk

Overview

This skill provides voice announcements, but it also tries to make them mandatory across future sessions and may send announcement text to an external TTS service.

Review this skill before installing. It should only be enabled if you deliberately want agent-wide spoken status updates, persistent agent behavior edits, startup checks, local audio caching, and network-backed TTS processing of announcement text. Avoid using it for confidential prompts unless announcements are disabled or rewritten to use generic, non-sensitive text.

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
  • System PersistenceInstalls backdoors, hooks, services, or scheduled tasks that survive the run
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Findings (5)

T01 · Skill Instruction Hijacking

Error
Location
SKILL.md:11
Finding

Mandatory Agent-Wide Audio Announcement Rules Hijack Normal Interaction Flow

Content
View full analysis
Remediation
View remediation

T02 · Agent Memory Poisoning

Error
Location
SKILL.md:47
Finding

Persistent Agent Memory and Identity Poisoning Through Integration Instructions

Content
View full analysis
Remediation
View remediation

T06 · System Persistence

Error
Location
SKILL.md:390
Finding

Proposed Session Hooks Establish Cross-Session Execution Persistence

Content
View full analysis
Remediation
View remediation

other

Error
Location
audio_announcement/announce_helper.py:237
Finding

Interaction Content Is Sent to a Network-Backed TTS Service Without Adequate Privacy Disclosure

Content
View full analysis
bool: cache_key = get_cache_key(text, voice) cached_file = CACHE_DIR / f"{cache_key}.mp3" if cached_file.exists(): logger.debug(f"使用缓存: {cached_file.name}") shutil.copy2(cached_file, output_file) return True logger.info(f"生成语音: {text[:40]}...") cmd = [ sys.executable, "-m", "edge_tts", "--text", text, "--voice", voice, "--write-media", output_file ] try: result = subprocess.run( cmd, capture_output=True, text=True, encoding='utf-8', errors='replace', timeout=30 ) ``` ```json "2.0.8": [ "✅ 播报本地化 - 所有播报仅在本机后台播放,不发送语音文件到聊天", "✅ 统一包装脚本 - scripts/announce.py 自动解析 skill 路径", "✅ 默认音量优化 - 配置文件默认 volume=0.1(10%)" ] ``` ### Technical Analysis The announcement text is supplied to the `edge_tts` module through its command-line interface. `edge-tts` is a network-backed speech-synthesis client, so uncached text must be processed through an external synthesis service to generate the MP3 response. The project states that playback is local and that audio files are not uploaded to chat. That statement does not adequately disclose that the source text may leave the local machine for speech synthesis. This becomes particularly sensitive because the Skill separately instructs the Agent to announce received instructions, work plans, progress, errors, and final summaries. The subprocess invocation uses an argument array and does not use `shell=True`; therefore, command injection through t ...[truncated 1230 chars]
Remediation
View remediation

T08 · Insecure Dependencies

Warning
Location
pyproject.toml:1
Finding

Mutable and Inconsistently Named Third-Party Dependencies Create Supply-Chain Risk

Content
View full analysis
=61.0", "wheel"] build-backend = "setuptools.build_meta" ``` ```toml dependencies = [ "edge-tts>=7.2.8", "pygame>=2.6.1; platform_system=='Windows'", ] ``` ```text # Beep - Small speaker requirements edge-tts>=7.2.8 pygame>=2.6.1 ``` ```bash pip install beep-announcement pygame ``` ```bash git clone https://github.com/wililam/beep-announcement.git cd beep-announcement pip install -e . ``` ### Technical Analysis Dependencies use open-ended lower bounds without a lockfile or cryptographic hashes. Installation can therefore resolve to future versions that were not reviewed during this audit. Build dependencies are similarly mutable. There is also a provenance inconsistency: the packaged project declares its name as `beep-skills`, while documentation instructs users to install `beep-announcement` and clone a repository named `beep-announcement`. The reviewed history does not prove that either referenced package is malicious. However, inconsistent naming makes it harder for users to verify that they are installing the audited artifact and increases dependency-confusion or wrong-package risk. Python packages and build backends can execute code during installation or import. Consequently, replacing a dependency or resolving an unexpected package version can lead to code execution with the installing user's privileges. ### Attack Path 1. A user follows the documentation and runs an unpinned `pip install` command. 2. The package resolver selects the newest version satisfying the lower-bound constraint. 3. The selected package version may differ from the version reviewed with this Skill. 4. Package build or inst ...[truncated 753 chars]
Remediation
View remediation
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (31)

Ssd 3

High
Category
Not specified by scanner
Confidence
99% confidence
Finding

The skill directly instructs the agent to speak the user's instruction content before acting, which can disclose private prompts, credentials, project names, or sensitive tasks to bystanders or recordings. Because this happens before any task execution, there is no opportunity to classify or redact sensitive content first.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill sets Chinese as the default broadcast language in persistent guidance without requesting user consent or presenting alternatives. This can override user preferences and create confusing or privacy-impacting behavior, especially in shared environments where spoken output may be understood by unintended listeners.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

High
Category
Not specified by scanner
Confidence
94% confidence
Finding

The configuration examples repeatedly normalize Chinese as the default language, reinforcing a behavior change without documenting consent or preference selection. Even in examples, this can lead integrators to deploy a privacy-affecting default broadly and unintentionally.

Content

No source excerpt is available for this finding.

Possible Typosquatting: 'pygame' resembles popular package 'pyyaml'

High
Category
Supply Chain
Confidence
70% confidence
Finding

Package name closely resembles a popular package, suggesting possible typosquatting. Attackers publish malicious packages with similar names to trick developers into installing them.

Content

No source excerpt is available for this finding.

Possible Typosquatting: 'pygame' resembles popular package 'pyyaml'

High
Category
Supply Chain
Confidence
70% confidence
Finding

Package name closely resembles a popular package, suggesting possible typosquatting. Attackers publish malicious packages with similar names to trick developers into installing them.

Content

No source excerpt is available for this finding.

Ssd 3

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

A rule requiring speech output on every interaction creates a broad natural-language exfiltration channel because user prompts, agent actions, and reply summaries may be spoken aloud to anyone nearby. The requirement is especially risky because it is mandatory and global rather than context-aware.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly instructs modifying multiple persistent workspace files that govern future agent behavior, but it does not clearly warn that these changes will survive the current task and affect later sessions. This creates a persistence mechanism that can silently alter trust boundaries and operating behavior over time.

Content

No source excerpt is available for this finding.

Ssd 3

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The examples normalize repeating user requests and response summaries in speech, which encourages developers to leak operational details and user data through audio output. Example code and docs are powerful defaults, so this pattern is likely to be copied into real deployments.

Content

No source excerpt is available for this finding.

Ssd 3

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The library usage examples embed user message content and delivered results directly in spoken announcements, creating an easy copy-paste path for data leakage. Although presented as convenience examples, they operationalize insecure handling of prompt and response data.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The configuration hard-codes default_lang to zh, which makes Chinese the default output language for announcements unless changed later. This is a natural-language locale policy concern because the skill selects a specific language by default rather than offering a neutral default or explicit user opt-in at first use.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · audio_announcement/announce_helper.py (reported line 260)May include surrounding context.

python
]
    
    try:
        result = subprocess.run(
            cmd,
            capture_output=True,
            text=True,

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · audio_announcement/announce_helper.py (reported line 385)May include surrounding context.

python
return False
    
    try:
        result = subprocess.run(
            player_cmd + [audio_file],
            capture_output=True,
            timeout=60

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · audio_announcement/announce_helper.py (reported line 586)May include surrounding context.

python
# 3. edge-tts 可用性(快速检查)
        try:
            result = subprocess.run(
                [sys.executable, "-m", "edge_tts", "--help"],
                capture_output=True,
                timeout=5,

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
83% confidence
Finding

This code file contains user-facing natural-language strings and module documentation that default to Chinese for key descriptions and later command feedback, without offering the user a choice of language or locale. The policy specifically calls for flagging language/locale constraints when a skill forces a specific language without opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The docstring states mandatory announcement rules entirely in Chinese and points to a rule set the script says must be followed every interaction. In addition, the main API defaults to lang="zh", which creates a language/locale default that may override user preference rather than offering a neutral choice or explicit opt-in.

Content

No source excerpt is available for this finding.

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · audio_announcement/scripts/announce_pygame.py (reported line 16)May include surrounding context.

python
complete: "上传完成"
    error: "网络连接失败"

详细规则见: skills/beep-skills/SKILL.md
"""

import os

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · audio_announcement/scripts/announce_pygame.py (reported line 116)May include surrounding context.

python
logger.debug(f"尝试生成 ({attempt}/{MAX_RETRIES})...")
            
            result = subprocess.run(
                cmd,
                capture_output=True,
                text=True,

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · audio_announcement/scripts/announce_pygame.py (reported line 296)May include surrounding context.

python
return False
    
    try:
        result = subprocess.run(
            player_cmd + [audio_file],
            capture_output=True,
            timeout=60,

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The script sets the announcement language to "zh" by default when the user does not provide a language argument. This enforces a specific locale choice rather than prompting for or preserving user preference, which is a natural-language policy concern under the language/locale rule.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The top-level docstring mixes English with Chinese ("小喇叭") in a user-facing description. Under the stated policy, forcing or assuming a specific language without opt-in can be a natural-language policy concern when no choice or justification is provided.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The module documentation says it falls back to a 'shell script', which suggests a script-based fallback mechanism. In the code, fallback behavior is implemented via direct subprocess execution of python -m edge_tts and platform player binaries like afplay, mpg123, ffplay, or aplay, with no shell script involved.

Content

No source excerpt is available for this finding.

Dynamic attribute access via getattr()

Low
Category
Dangerous Code Execution
Confidence
50% confidence
Finding

Dynamic getattr() with a non-literal attribute name can access arbitrary object attributes, potentially bypassing access controls.

Content

Scanner excerpt · audio_announcement/announce_helper.py (reported line 162)May include surrounding context.

python
# 全局配置
_config = AnnouncementConfig.load()
setup_logging(getattr(logging, _config.log_level))

# ============ 统计与监控 ============
class StatsCollector:

Dynamic attribute access via getattr()

Low
Category
Dangerous Code Execution
Confidence
50% confidence
Finding

Dynamic getattr() with a non-literal attribute name can access arbitrary object attributes, potentially bypassing access controls.

Content

Scanner excerpt · audio_announcement/announce_helper.py (reported line 527)May include surrounding context.

python
# 全局配置
_config = AnnouncementConfig.load()
setup_logging(getattr(logging, _config.log_level))

# ============ 统计与监控 ============
class StatsCollector:

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The top-level docstring describes this as a 'PyGame Version' using pygame.mixer for playback, which suggests a narrowly scoped local playback implementation. In reality, the script also synthesizes speech by spawning python -m edge_tts and falls back to OS-level media players, so the documentation understates and partially misrepresents the implemented behavior.

Content

No source excerpt is available for this finding.

Unverifiable Dependency: setuptools has 10 known advisory(ies) (CVE-2013-1633 (Setuptools vulnerable to Man-in-the-middle attacks); CVE-2025-47273 (setuptools has a path traversal vulnerability in PackageIndex.download that lead); CVE-2024-6345 (setuptools vulnerable to Command Injection via package URL) +7 more), but the manifest does not pin a version, so it is unknown whether the installed release is affected

Low
Category
Supply Chain
Confidence
40% confidence
Finding

Dependency has known vulnerabilities (CVEs). Using packages with unpatched security flaws exposes the environment to known exploits.

Content

No source excerpt is available for this finding.