← Back to Blog

We Scanned the Top 50 ClawHub Skills — Here's What We Found

88% scored Grade A. Zero CRITICAL findings. But 66% of the most popular AI agent tools contain no code at all — and that raises its own questions.

We Scanned the Top 50 ClawHub Skills — Here's What We Found

Update: This is the original March 25 scan. For the latest data (March 27 refresh), see We Re-Scanned the Top 50 — Things Have Changed.

We took our V(g) security scanner and ran it against the Top 50 most-installed ClawHub Skills — totaling over 1.25 million downloads. The goal was simple: apply the same static analysis we use for Rotifer Genes to the most popular tools in the Claw ecosystem, and publish the results.

The headline: zero CRITICAL findings across all 50 Skills. No eval(), no child_process, no code obfuscation.

But the details tell a more nuanced story.


Grade Distribution

GradeCount%Meaning
A4488%Zero CRITICAL + zero HIGH
B48%Zero CRITICAL + ≤2 HIGH (explainable)
C24%Zero CRITICAL + >2 HIGH
D00%

88% of the Top 50 received the highest grade. That’s a strong signal for the ecosystem’s security baseline — at least among the most popular tools.


Most Skills Are Pure Prompt

CategoryCount%
With code files (.ts/.js/.py/.sh)1734%
Pure prompt (SKILL.md only)3366%

66% of the Top 50 are prompt-only Skills. They contain no executable code — only a SKILL.md instruction file. These are inherently safe from code-level attacks (though prompt injection is a separate concern outside V(g) scope).

This ratio raises an interesting question: if most popular AI tools are just prompts, what does “quality” mean beyond security? Documentation completeness, error handling patterns, and claim-vs-reality alignment become the more meaningful dimensions.


Most Common Risk Patterns

Among the 34% that ship code:

RuleHitsSeverityDescription
S-0712MEDIUMFile system operations (readFile, writeFile)
S-0510HIGHEnvironment variable access (process.env)
S-044HIGHExternal HTTP communication (fetch)

S-07 (File I/O) is the most common — many Skills need to read/write configuration files. Expected for CLI tooling.

S-05 (Env Access) is standard practice for API key management. The concern isn’t reading env vars per se, but which vars and where the values are sent.

Every finding was explainable and context-appropriate.


Skills with Findings

SkillGradeFindingsDownloadsKey Patterns
elite-longterm-memoryB819,322Heavy file I/O (memory persistence)
imap-smtp-emailB716,931File I/O + HTTP (email protocol)
stock-analysisC620,778Env vars for API keys (Yahoo Finance)
brave-searchC325,056HTTP requests (search API)
nano-banana-proB131,591Env var for Gemini API key
free-rideB126,138Env var for OpenRouter API key

All findings are legitimate operations for the Skills’ intended functionality.


Comparison with ClawHavoc

In February 2026, the ClawHavoc incident revealed that ~12% of ClawHub’s 38,000+ Skills had been compromised. Our Top 50 scan shows a markedly healthier profile:

MetricClawHavoc (Full Registry)V(g) Top 50
CRITICAL findings12% infection rate0%
Code obfuscationMultiple cases0 hits
Suspicious execWidespread0 hits
External commsUndisclosed endpoints4 hits (all to known APIs)

The most popular Skills have stronger security hygiene — likely because high-visibility tools attract more scrutiny, 28 of the 50 are Certified Skills that undergo review, and established authors maintain quality.

But what about the other 12,950?


Methodology


What This Means

The data suggests two things:

  1. The top of the ecosystem is clean. Security tooling like VirusTotal + manual review has kept the most popular Skills safe. V(g) confirms this with a different methodology.

  2. Security is necessary but not sufficient. When 66% of popular tools are just prompts, code-level security scanning catches one dimension. Quality scoring — documentation, error handling, claim verification — addresses the rest.

V(g) is one layer of trust. We think the ecosystem needs more layers. If you’re interested in quality scoring as a complement to security scanning, we’d love to hear your perspective.


Try It

Scan any Skill or Gene with one command:

Terminal window
npx @rotifer/playground vg <path>

Badge your repo: rotifer.ai/badge

Full scanner docs: rotifer.dev/docs/cli/vg


Report by Rotifer Protocol. Data, methodology, and scanner are open source.