Back to skill

Security audit

custom-youtube-summarize

Security checks for vulnerabilities and agentic risk

Overview

This skill appears to do what it says: run a local Python script to fetch a YouTube transcript and summarize it.

Before installing, expect the skill to contact YouTube for the requested video and pass the resulting transcript into the LLM for summarization. Avoid using it for private or sensitive video content unless that data flow is acceptable.

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
Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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
Findings (119)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The finding explicitly says the code does not parse YouTube URLs, does not extract transcripts, and instead performs generic network transport with browser/Node interop features. That is a severe description-behavior mismatch and strongly suggests deceptive or repurposed code with unnecessary capability.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The finding explicitly says the code does not parse YouTube URLs, does not extract transcripts, and instead performs generic network transport with browser/Node interop features. That is a severe description-behavior mismatch and strongly suggests deceptive or repurposed code with unnecessary capability.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The finding explicitly says the code does not parse YouTube URLs, does not extract transcripts, and instead performs generic network transport with browser/Node interop features. That is a severe description-behavior mismatch and strongly suggests deceptive or repurposed code with unnecessary capability.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The finding explicitly says the code does not parse YouTube URLs, does not extract transcripts, and instead performs generic network transport with browser/Node interop features. That is a severe description-behavior mismatch and strongly suggests deceptive or repurposed code with unnecessary capability.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The finding explicitly says the code does not parse YouTube URLs, does not extract transcripts, and instead performs generic network transport with browser/Node interop features. That is a severe description-behavior mismatch and strongly suggests deceptive or repurposed code with unnecessary capability.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The finding explicitly says the code does not parse YouTube URLs, does not extract transcripts, and instead performs generic network transport with browser/Node interop features. That is a severe description-behavior mismatch and strongly suggests deceptive or repurposed code with unnecessary capability.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The finding explicitly says the code does not parse YouTube URLs, does not extract transcripts, and instead performs generic network transport with browser/Node interop features. That is a severe description-behavior mismatch and strongly suggests deceptive or repurposed code with unnecessary capability.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The finding explicitly says the code does not parse YouTube URLs, does not extract transcripts, and instead performs generic network transport with browser/Node interop features. That is a severe description-behavior mismatch and strongly suggests deceptive or repurposed code with unnecessary capability.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The finding explicitly says the code does not parse YouTube URLs, does not extract transcripts, and instead performs generic network transport with browser/Node interop features. That is a severe description-behavior mismatch and strongly suggests deceptive or repurposed code with unnecessary capability.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The finding explicitly says the code does not parse YouTube URLs, does not extract transcripts, and instead performs generic network transport with browser/Node interop features. That is a severe description-behavior mismatch and strongly suggests deceptive or repurposed code with unnecessary capability.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The finding explicitly says the code does not parse YouTube URLs, does not extract transcripts, and instead performs generic network transport with browser/Node interop features. That is a severe description-behavior mismatch and strongly suggests deceptive or repurposed code with unnecessary capability.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The finding explicitly says the code does not parse YouTube URLs, does not extract transcripts, and instead performs generic network transport with browser/Node interop features. That is a severe description-behavior mismatch and strongly suggests deceptive or repurposed code with unnecessary capability.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The finding explicitly says the code does not parse YouTube URLs, does not extract transcripts, and instead performs generic network transport with browser/Node interop features. That is a severe description-behavior mismatch and strongly suggests deceptive or repurposed code with unnecessary capability.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The finding explicitly says the code does not parse YouTube URLs, does not extract transcripts, and instead performs generic network transport with browser/Node interop features. That is a severe description-behavior mismatch and strongly suggests deceptive or repurposed code with unnecessary capability.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The finding explicitly says the code does not parse YouTube URLs, does not extract transcripts, and instead performs generic network transport with browser/Node interop features. That is a severe description-behavior mismatch and strongly suggests deceptive or repurposed code with unnecessary capability.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The finding explicitly says the code does not parse YouTube URLs, does not extract transcripts, and instead performs generic network transport with browser/Node interop features. That is a severe description-behavior mismatch and strongly suggests deceptive or repurposed code with unnecessary capability.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The finding explicitly says the code does not parse YouTube URLs, does not extract transcripts, and instead performs generic network transport with browser/Node interop features. That is a severe description-behavior mismatch and strongly suggests deceptive or repurposed code with unnecessary capability.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The finding explicitly says the code does not parse YouTube URLs, does not extract transcripts, and instead performs generic network transport with browser/Node interop features. That is a severe description-behavior mismatch and strongly suggests deceptive or repurposed code with unnecessary capability.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The finding explicitly says the code does not parse YouTube URLs, does not extract transcripts, and instead performs generic network transport with browser/Node interop features. That is a severe description-behavior mismatch and strongly suggests deceptive or repurposed code with unnecessary capability.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The finding explicitly says the code does not parse YouTube URLs, does not extract transcripts, and instead performs generic network transport with browser/Node interop features. That is a severe description-behavior mismatch and strongly suggests deceptive or repurposed code with unnecessary capability.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The finding explicitly says the code does not parse YouTube URLs, does not extract transcripts, and instead performs generic network transport with browser/Node interop features. That is a severe description-behavior mismatch and strongly suggests deceptive or repurposed code with unnecessary capability.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The finding explicitly says the code does not parse YouTube URLs, does not extract transcripts, and instead performs generic network transport with browser/Node interop features. That is a severe description-behavior mismatch and strongly suggests deceptive or repurposed code with unnecessary capability.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The finding explicitly says the code does not parse YouTube URLs, does not extract transcripts, and instead performs generic network transport with browser/Node interop features. That is a severe description-behavior mismatch and strongly suggests deceptive or repurposed code with unnecessary capability.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The finding explicitly says the code does not parse YouTube URLs, does not extract transcripts, and instead performs generic network transport with browser/Node interop features. That is a severe description-behavior mismatch and strongly suggests deceptive or repurposed code with unnecessary capability.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The finding explicitly says the code does not parse YouTube URLs, does not extract transcripts, and instead performs generic network transport with browser/Node interop features. That is a severe description-behavior mismatch and strongly suggests deceptive or repurposed code with unnecessary capability.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.