YouTube AI Videos

Security checks across malware telemetry and agentic risk

Overview

This skill does what it says: it uses a user-provided YouTube API key to fetch recent AI-related YouTube videos, with no evidence of hidden or destructive behavior.

Install only if you are comfortable providing a YouTube Data API key and making requests to Google/YouTube. Prefer a restricted YouTube Data API v3 key stored in ~/.openclaw/secrets/youtube_api_key.txt with tight permissions, and avoid putting the key in config.json or a synced shell profile.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
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)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 95% confidence
Finding: The skill documentation indicates capabilities to read environment variables, read local files, and make network requests, but it does not declare corresponding permissions. This creates a transparency and consent problem: users may invoke the skill without realizing it can access secrets from the environment or filesystem and transmit data to external services.

Missing User Warnings

Low

Confidence: 93% confidence
Finding: The README instructs users to persist the YouTube API key in shell profile files such as ~/.zshrc or ~/.bashrc, which stores the secret in plaintext and can increase accidental exposure through backups, dotfile syncing, screen sharing, or local account compromise. Although this is common documentation practice, it normalizes weaker secret-handling compared with the safer secrets-file option already described.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal