ClawHub
Back to skill

Security audit

YouTube Search

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward YouTube transcript/search helper that uses a disclosed third-party API and does not include hidden code, persistence, or destructive behavior.

Install only if you are comfortable using BulkTranscripts and sending search terms, video URLs or IDs, channel handles, and transcript requests to that service. Keep the API key private and avoid submitting confidential research topics unless that provider is approved for your use.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill directs use of a third-party API and transmission of search queries, video IDs/URLs, channel handles, and potentially transcript retrieval requests without clearly warning that this user-supplied data leaves the local environment. This can create privacy and data-governance risk, especially if users submit sensitive research topics, internal investigation subjects, or confidential watchlists.

Description-Behavior Mismatch

Low
Confidence
98% confidence
Finding
The manifest and top-level documentation consistently frame the skill as a YouTube-focused search and transcript tool. However, the documented `transcript` parameter explicitly accepts a TikTok video URL, expanding the skill beyond the stated YouTube-only scope.

Static analysis

No suspicious patterns detected.