Security audit

NotebookLM Audio Generator

Security checks for vulnerabilities and agentic risk

Overview

The skill’s main NotebookLM audio workflow is coherent, but its setup asks users to run unverified third-party code before authenticating and uploading documents.

Review the setup steps before installing. Use pinned versions or a reviewed commit for the CLI and epub2txt, avoid running the GitHub run.sh script until you have inspected it, and only upload documents you are comfortable sending to NotebookLM.

A.I.G

Vulnerability Patterns

Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Insecure DependenciesIntroduces malicious components through unsafe dependency sources
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
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally

Findings (2)

T03 · Remote Payload Retrieval and Execution

Error

Location: SKILL.md:33
Finding: Execution of an Unpinned Mutable Remote Repository
Content: View full analysis
Remediation: View remediation

T08 · Insecure Dependencies

Warning

Location: SKILL.md:21
Finding: Unpinned Installation of a Third-Party Python Package
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Rp1

Low

Category: MCP Rug Pull
Confidence: 60% confidence
Finding: pip install without ==version installs the latest release, which could include malicious changes.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: This markdown skill description directs the agent to save an MP3 file to the destination path, which is a file-write operation affecting the user's filesystem. Although the destination is user-selected, the description does not explicitly warn the user that a file will be created there; the separate notice about generation time does not disclose this behavior.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.