Back to skill

Security audit

Youtube Data CLI

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed YouTube management helper, but it asks users to install an unpinned credential-handling CLI and enables broad account-changing actions without clear confirmation safeguards.

Review this skill before installing if you intend to connect a real YouTube account. Prefer a pinned, inspected, local or isolated install of the CLI, grant the narrowest OAuth scope needed, protect refresh tokens, and require explicit confirmation before uploads, deletes, moderation, subscription changes, or channel configuration changes.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (1)

T08 · Insecure Dependencies

Error
Location
SKILL.md:30
Finding

Unpinned Global Installation of a Credential-Handling Third-Party Package

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 47)May include surrounding context.

md
1. `--credentials <path>` flag (per-command)
2. `YOUTUBE_API_KEY`, `YOUTUBE_CLIENT_ID`, `YOUTUBE_CLIENT_SECRET`, `YOUTUBE_REFRESH_TOKEN` env vars
3. `~/.config/youtube-data-cli/credentials.json` (auto-detected)

Recommended OAuth scope: `https://www.googleapis.com/auth/youtube` (full access). Add `https://www.googleapis.com/auth/youtube.upload` if using narrower scopes but need video uploads.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger list includes broad phrases like "YouTube", "subtitles", and "like video", which can cause this skill to activate in loosely related contexts and steer an agent into using a high-privilege tool unexpectedly. Because the skill supports write and destructive operations, overbroad invocation increases the chance of unintended account actions from ambiguous user requests.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill advertises account-modifying and destructive operations such as upload, update, delete, rating, subscriptions, and moderation without any warning, guardrails, or confirmation guidance. In an agent setting, this creates a real risk that ordinary user requests could be translated into irreversible actions against a YouTube account without informed consent.

Content

No source excerpt is available for this finding.