ClawHub
Back to skill

Security audit

youtube-research

Security checks across malware telemetry and agentic risk

Overview

The skill is mostly a YouTube research helper, but its included shell helper is broader than the stated YouTube-only purpose and can send the API key to an overridden endpoint.

Review this before installing if you want a strictly YouTube-only skill. Use it only in an environment where CRAWLORA_API_BASE is trusted or unset, and avoid letting prompts or workflows call non-YouTube Crawlora paths through the included helper.

SkillSpector

By NVIDIA
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)

Tp4

High
Category
MCP Tool Poisoning
Confidence
90% confidence
Finding
The skill claims to be limited to YouTube research, but the referenced helper script and endpoint documentation appear capable of calling arbitrary Crawlora paths, including non-YouTube services and generic POST requests. That mismatch is dangerous because users and reviewers may trust the skill with broader network access than disclosed, enabling data exfiltration, policy bypass, or unintended third-party actions under a misleading description.

External Transmission

Medium
Category
Data Exfiltration
Content
set -euo pipefail

: "${CRAWLORA_API_KEY:?Set CRAWLORA_API_KEY first — get a free key at https://crawlora.net?utm_source=github&utm_medium=referral&utm_campaign=crawlora-skills}"
base="${CRAWLORA_API_BASE:-https://api.crawlora.net/api/v1}"

method="GET"
body=""
Confidence
67% confidence
Finding
https://api.crawlora.net/

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
SKILL.md:23