YT Meta - YouTube Metadata Extractor

SAFE max severity MEDIUMSkillSpector Safe 0 registry clawhub.ai last scanned 2026-02-07 1 scan

Verdict safe, but 3 findings (2 medium, 1 low), mainly command injection, social engineering, resource abuse. Most recent scan 2026-02-07.

This skill presents MODERATE security risks primarily related to supply chain security and unverified third-party dependencies. The skill itself contains no malicious code (no script files are included), but it instructs the agent to install and execute an external npm package globally without version pinning or verification. The main concerns are: (1) Supply chain risk from unverified npm package installation, (2) Lack of transparency about what the external tool actually does with data, (3) Missing optional metadata that would help users assess compatibility and tool requirements, (4) Potential for resource exhaustion with unbounded data collection operations. The skill would benefit from adding version pinning, security disclosures, and clearer documentation about the external dependency's behavior and data handling.
Scanner's overall assessment (LLM analyzer)

Findings3

Critical0

High0

Medium2

Low1

Analyzersstatic llm meta

Second scanner: NVIDIA SkillSpector

VerdictSafe 0

Score0 / 100

Issues0

Version2.12.0 (static)

Independent static run, no language model, over the same files as the Cisco scan above. How the two scanners compare across the whole corpus: Two scanners, one corpus.

What this skill does

Extract YouTube video info, channel stats, playlists, comments. No API key required. Free CLI tool for content research and analysis.

Package: 1 file, 2.1 KB
SKILL.md: 245 words, 11 sections
Code: None. Instructions only.

SKILL.md covers: YT Meta · Installation · Commands · Video Metadata · Channel Info · Playlist · Search · Comments · Output Formats · Example Output · Common Use Cases

Findings

MEDIUM Unverified Third-Party Package Installation Command Injectionllm

The skill instructs the agent to install a third-party npm package 'yt-meta-cli' globally without version pinning or provenance verification. This creates a supply chain risk where a malicious or compromised package could be installed on the user's system with global permissions.

SKILL.md:7

npm install -g yt-meta-cli (no version specified, global installation)

Remediation: 1) Pin to a specific verified version (e.g., 'npm install -g yt-meta-cli@1.2.3'), 2) Add package verification steps (checksum, signature), 3) Document the package source and maintainer, 4) Consider using npx for non-persistent execution, 5) Warn users about global installation implications.

MEDIUM Potential Social Engineering via Unverified External Tool Social Engineeringllm

The skill description claims 'No API key required. Free CLI tool' which could be used to build false trust. The skill delegates all functionality to an external npm package (yt-meta-cli) whose behavior, safety, and data handling practices are not verified within the skill itself. Users may trust the skill based on its description without understanding they're installing and running unverified third-party code.

SKILL.md

Description: 'No API key required. Free CLI tool for content research and analysis' - delegates to unverified external package

Remediation: 1) Add clear disclosure that this skill installs and runs third-party software, 2) Include security warnings about external dependencies, 3) Provide links to the package's source code for user review, 4) Document what data the external tool may access or transmit, 5) Consider implementing the functionality directly rather than depending on external packages.

LOW Unbounded Data Collection Without Limits Resource Abusellm

Several commands allow potentially unbounded data collection (e.g., '--all' for entire playlists, '--limit 500' for comments, channel videos without default limits). While limits can be specified, the instructions don't warn about resource consumption or provide sensible defaults, which could lead to excessive API calls, memory usage, or long-running operations.

SKILL.md

Commands like 'yt-meta playlist PLxxx --all', 'yt-meta comments VIDEO_ID --limit 500', 'yt-meta channel @mkbhd --videos --limit 500' allow large-scale data collection

Remediation: 1) Document recommended limits for different use cases, 2) Add warnings about resource consumption for large operations, 3) Suggest incremental/paginated approaches for large datasets, 4) Implement or document timeout mechanisms, 5) Provide guidance on appropriate limit values.

What is in the package

File	Kind	Size
`SKILL.md`	doc	2.1 KB

External hosts referenced

github.com lxgicstudios.com x.com youtu.be youtube.com

Hostnames that appear in the skill's files. Referencing a host is not a finding; compare against the findings above and the skill's stated purpose.

Package contents recorded 2026-10-22. The scan above ran against the version current at scan time; the two can differ if the skill has since been updated.

What we checked

Static analyzer. Pattern rules over SKILL.md and bundled files: known-bad commands, exfiltration URLs, secrets, obfuscation.
Llm analyzer. A language model reads the skill and reports intent-level issues the rules cannot express.
Meta analyzer. A second model pass that validates, deduplicates and re-scores the other analyzers' findings.

What we did not check

Runtime behaviour. The skill was not executed; findings come from reading its files.
Anything fetched at install or run time, including remote scripts, package dependencies, and URLs the skill tells the agent to open.
Content the analyzers cannot read: images, binaries, and some non-English text.
Known scanner bypass classes. See the methodology and limitations page.

Sources

Repository: https://clawhub.ai/skills/yt-meta
Raw scan result: yt-meta-youtube-metadata-extractor-scan.json
Badge for your README: ![skillscan.io](https://skillscan.io/badge/clawhub-ai-yt-meta-youtube-metadata-extractor.svg)
Request a re-scan