audio-quality-check

• Outcome: Review
• Latest audit: Sep 16, 2026 · 5:01 AM UTC
• Version: 0.1.4

Overview

The skill appears purpose-aligned, but it analyzes sensitive call recordings and can leave decoded audio in temporary storage while also printing recording metadata.

Review before installing if your recordings contain confidential calls. Run it only on recordings you intend to expose to the agent and terminal output, prefer an isolated Python environment, consider pinned dependencies, and manually check or clear audio_analysis_* temporary directories after use, especially after --echo mode or failed runs.

A.I.G

Vulnerability Patterns

• Insecure Dependencies: Introduces malicious components through unsafe dependency sources
• Insecure Skill Coding Practices: Finds exploitable flaws such as hardcoded secrets or command injection
• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review

Findings (2)

T08 · Insecure Dependencies

Warning

• Location: SKILL.md:34

Finding

Unpinned Third-Party Python Dependencies Create a Supply-Chain Risk

Content

View full analysis

Remediation

View remediation

soundfile== scipy== pyloudnorm== pesq== pystoi== librosa== ``` 2. Generate cryptographic hashes for every direct and transitive package. 3. Require hash validation during installation: ```bash python3 -m pip install --require-hashes -r requirements.txt ``` 4. Use a dependency lock or constraints file so transitive dependency resolution is reproducible. 5. Document the trusted package index and avoid implicitly using arbitrary mirrors or additional indexes. 6. Run dependency vulnerability and provenance checks in continuous integration. 7. Review and update pinned packages through a controlled process rather than allowing automatic installation of newly published releases. ]]>

T09 · Insecure Skill Coding Practices

Warning

• Location: scripts/analyze_recording.py:367

Finding

Decoded Recording Data Can Remain in Temporary Storage

Content

View full analysis

Remediation

View remediation

SkillSpector

Vulnerability Patterns

• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Behavioral AST: exec() Call, eval() Call, Dynamic Import
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration

Findings (8)

Undeclared Tool Scope

Medium

• Category: MCP Least Privilege
• Confidence: 94% confidence

Finding

The skill instructs the agent to run shell commands and read user-supplied recording paths, but it does not declare any explicit tool scope such as allowed tools or permissions. This creates an overbroad execution surface where an agent may invoke shell/file capabilities without policy constraints, increasing the risk of unintended access to arbitrary local files or unsafe command execution patterns if the path or invocation is mishandled.

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/analyze_recording.py (reported line 48)May include surrounding context.

python

def probe_tracks(audio_path):
    """Get track info via ffprobe. Returns list of stream dicts."""
    result = subprocess.run(
        [
            "ffprobe", "-v", "quiet", "-print_format", "json",
            "-show_streams", str(audio_path)

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/analyze_recording.py (reported line 63)May include surrounding context.

python

def extract_track(audio_path, track_index, output_path, target_sr=16000):
    """Extract a single track to mono WAV at target sample rate."""
    subprocess.run(
        [
            "ffmpeg", "-y", "-v", "quiet",
            "-i", str(audio_path),

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 90% confidence

Finding

The script prints recording metadata such as title, app name, creation time, and speaker names directly to stdout without any consent prompt, redaction, or warning. In this skill context, the tool explicitly analyzes call recordings, so exposing metadata and derived audio-quality details can leak sensitive personal or call-related information into logs, terminal history, shared output, or downstream agent traces.

Content

No source excerpt is available for this finding.

Scope Creep

Low

• Category: Excessive Agency
• Confidence: 70% confidence

Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · LICENSE.txt (reported line 27)May include surrounding context.

text

permissions granted by this License.

"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation source, and
configuration files.

"Object" form shall mean any form resulting from mechanical transformation or

Scope Creep

Low

• Category: Excessive Agency
• Confidence: 70% confidence

Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · LICENSE.txt (reported line 31)May include surrounding context.

text

permissions granted by this License.

"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation source, and
configuration files.

"Object" form shall mean any form resulting from mechanical transformation or

Scope Creep

Low

• Category: Excessive Agency
• Confidence: 70% confidence

Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · LICENSE.txt (reported line 54)May include surrounding context.

text

permissions granted by this License.

"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation source, and
configuration files.

"Object" form shall mean any form resulting from mechanical transformation or

Scope Creep

Low

• Category: Excessive Agency
• Confidence: 70% confidence

Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · LICENSE.txt (reported line 147)May include surrounding context.

text

permissions granted by this License.

"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation source, and
configuration files.

"Object" form shall mean any form resulting from mechanical transformation or

Static analysis

No suspicious patterns detected.