ClawHub
Back to skill

Security audit

YouTube Content Analyzer

Security checks for vulnerabilities and agentic risk

Overview

This skill appears to be a normal YouTube/transcript analysis helper, with local report-writing and manual install risks users should review before use.

Before installing, read the downloaded SKILL.md and analyze_content.py, prefer a pinned commit or verified release instead of the mutable main branch, and delete generated reports if they contain private transcripts. Do not provide sensitive video transcripts unless local persistence is acceptable.

SkillSpector

Vulnerability Patterns
  • Rogue AgentSelf-Modification, Session Persistence
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill invokes Python scripts, shell commands, network fetches, and writes files under the user's home directory, yet it declares no explicit permissions or trust boundaries. This creates a capability mismatch that can cause agents or users to execute file and shell operations without clear disclosure or policy gating.

Missing User Warnings

Low
Confidence
83% confidence
Finding
The script writes reports that embed raw transcript content to disk, potentially including sensitive or copyrighted material, without meaningful notice, consent flow, or data-handling controls. In this skill context, users may supply private subtitle/transcript files or URLs and not realize the content is being persisted locally in a reusable report.

Session Persistence

Medium
Category
Rogue Agent
Content
```bash
# macOS / Linux
mkdir -p ~/.agents/skills/youtube-content-analyzer/scripts
curl -o ~/.agents/skills/youtube-content-analyzer/SKILL.md \
  https://raw.githubusercontent.com/mcbaivn/openclaw-skills-mcbai/main/skills/youtube/youtube-content-analyzer/SKILL.md
curl -o ~/.agents/skills/youtube-content-analyzer/scripts/analyze_content.py \
Confidence
91% confidence
Finding
The installation instructions create persistent directories under ~/.agents and download executable skill content and a Python script from a remote GitHub source into that location. Persistent modification of agent-controlled directories increases risk because remote content can be updated, replaced, or later executed as a trusted local skill, making supply-chain compromise and long-term persistence more dangerous.

Static analysis

No suspicious patterns detected.