Back to skill

Security audit

Audio Command Handler

Security checks for vulnerabilities and agentic risk

Overview

This skill turns audio into agent commands and can upload long results without a clear confirmation step, so it needs Review before use.

Install only if you intentionally want audio to drive agent actions, and require the agent to show the transcript and ask before executing commands or uploading results. Avoid using it with private recordings, credentials, or sensitive business content unless the transcription and upload services are trusted and access-controlled.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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 (4)

T01 · Skill Instruction Hijacking

Error
Location
SKILL.md:17
Finding

Untrusted Audio Transcription Is Automatically Promoted to an Agent Command

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:23
Finding

Length-Based Automatic Upload Can Disclose Sensitive Generated Content

Content
View full analysis
58 characters: save to file, upload via `uploader` skill, return URL ``` ### Technical Analysis The Skill selects external upload behavior solely according to whether the generated result exceeds 58 characters. It does not require user consent, inspect the result for sensitive information, identify the upload destination, or state its access controls and retention policy. Generated results may contain private transcript content, personal information, credentials spoken in a recording, confidential business information, or contextual data acquired through other Agent tools. Character count is unrelated to sensitivity and therefore does not provide an appropriate authorization boundary. The uploader implementation is outside this audited project. Its destination, authentication, link visibility, encryption, and retention behavior could not be verified. The issue is the Skill's unconditional instruction to transfer content rather than a confirmed defect in that external uploader. ### Attack Path 1. A user supplies an audio file together with a text command. 2. The transcript or command causes the result to include sensitive information. 3. The generated result exceeds 58 characters. 4. The Skill saves the result to a file and invokes the external uploader without requesting informed consent. 5. The uploader transfers the result to an external destination and returns a URL. 6. The content becomes accessible according to the external ser ...[truncated 527 chars]
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/handle_audio.py:75
Finding

Predictable Workspace Filename Allows Symlink-Based File Overwrite

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Note
Location
scripts/handle_audio.py:237
Finding

Caller-Controlled Output Path Can Overwrite Existing Files

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (17)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The description presents this skill as an active command handler that transcribes audio and then executes commands, with special handling for long results via upload. The actual script only performs transcription and prepares/prints the resulting command/context information. No subprocess or internal logic executes the derived command text. The save_and_upload function is present but unused, and there is no length check for 58 characters or automatic uploader invocation. These are material behavioral gaps relative to the declared purpose, so this is a mismatch.

Content

No source excerpt is available for this finding.

Missing User Warnings

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill states that long results are automatically saved locally and uploaded, but it does not warn users that their data may be persisted and shared via a generated link. Automatic storage and upload can expose sensitive transcripts or derived content beyond the immediate chat context.

Content

No source excerpt is available for this finding.

Missing User Warnings

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill states that long results are automatically saved locally and uploaded, but it does not warn users that their data may be persisted and shared via a generated link. Automatic storage and upload can expose sensitive transcripts or derived content beyond the immediate chat context.

Content

No source excerpt is available for this finding.

Ssd 4

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

This workflow creates a direct path from untrusted audio input to command execution with no approval checkpoint. In skill context, that is especially dangerous because transcription errors, hidden spoken instructions, or maliciously crafted audio could cause the agent to perform unintended actions using the transcript as if it were trusted user input.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
80% confidence
Finding

The skill invokes shell commands and writes files, but it declares no tool scope or permissions boundaries. That makes the operational surface larger and less auditable, increasing the risk of unintended command execution or file writes when the skill is auto-invoked.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The activation description is broad enough that the skill may trigger on ordinary audio messages rather than only on clearly intended command workflows. In this skill's context, over-broad activation is dangerous because it can route benign audio into transcription, command handling, and possible downstream upload behavior without clear user intent.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The instruction to 'process audio messages and execute them as commands' is ambiguous about when execution should occur, which can cause unsafe automatic handling of untrusted speech. Because speech is inherently error-prone and may include ambient or adversarial content, ambiguity materially increases the chance of unintended execution.

Content

No source excerpt is available for this finding.

Ssd 3

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

Automatically injecting transcribed speech as context into a text command can leak sensitive spoken content into unrelated processing steps and tools. This is risky because users may provide an innocuous text instruction while the audio contains private information that then gets forwarded, summarized, stored, or uploaded without deliberate review.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The module docstring says the script will 'execute commands' in both the audio-only and audio+text scenarios, matching the manifest's promise to execute the transcription or text command. However, the code never invokes any command execution logic; it only transcribes audio, selects a command string, and prints or serializes that data.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The docstring explicitly states that in the audio+text case the script will 'execute the text command with transcription context,' and likewise for audio-only it says the transcription is executed as a command. In reality, the code only assigns command/context variables and prints them or emits JSON, which directly contradicts the documented behavior.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

Both the module docstring and manifest describe automatic handling where results longer than 58 characters are saved to a file and uploaded via the uploader skill. Although a save_and_upload helper exists, main() never calls it, never checks result length, and never uploads anything automatically.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

The script forwards user audio to an external transcription component without any visible consent prompt, warning, or data-classification check. In an agent skill that handles potentially sensitive voice content and may treat the transcript as a command, undisclosed transmission can expose private information and create compliance/privacy risk.

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 · scripts/handle_audio.py (reported line 35)May include surrounding context.

python
raise FileNotFoundError(f"Transcription script not found: {TRANSCRIBE_SCRIPT}")
    
    # Run transcription
    result = subprocess.run(
        ["python3", str(TRANSCRIBE_SCRIPT), audio_path, "--output-format", "json"],
        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 · scripts/handle_audio.py (reported line 76)May include surrounding context.

python
def save_and_upload(content: str, filename_prefix: str = "audio_result") -> dict:
    """Save content to HTML file and upload via uploader skill."""
    # Create temp file with HTML extension
    timestamp = subprocess.check_output(["date", "+%Y%m%d_%H%M%S"], text=True).strip()
    filename = f"{filename_prefix}_{timestamp}.html"
    temp_path = WORKSPACE_DIR / filename

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 · scripts/handle_audio.py (reported line 168)May include surrounding context.

python
if not UPLOAD_SCRIPT.exists():
        raise FileNotFoundError(f"Upload script not found: {UPLOAD_SCRIPT}")
    
    result = subprocess.run(
        ["python3", str(UPLOAD_SCRIPT), str(temp_path)],
        capture_output=True,
        text=True,

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

The example commands and sample returned text are exclusively in Chinese, and the skill does not indicate that output language follows user preference or can be selected. This may create an implicit language default without opt-in, especially since the skill claims support for both Chinese and English.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The generated HTML hard-codes lang="zh-CN" and uses Chinese-only title text, which imposes a specific locale in the output regardless of user preference. The policy allows locale constraints only when user choice is offered or the restriction is clearly documented and justified, neither of which appears here.

Content

No source excerpt is available for this finding.