Security

How every submission is reviewed before publishing.

2,847

Scanned

Quarantined

99.2%

Pass rate

<2s

Avg scan time

Scanning pipeline

Scan for known prompt injection phrases, credential exfiltration patterns, hidden unicode characters, and obfuscated code.

Check all embedded URLs against malware databases. Flag IP addresses, URL shorteners, and suspicious domains.

Claude reviews content intent, risk scoring, and identifies subtle injection attempts that pattern matching misses.

Low risk + verified author → auto-approve. Medium risk → manual review. High risk → quarantine.

Prompt injection attempts

Credential exfiltration

Hidden unicode characters

Base64-encoded commands

Malicious URLs and domains

Obfuscated code patterns

Zero-width character injection

Unauthorized network calls

🆕

New

Account created. Full review on all submissions.

✓

Member

3+ approved submissions, 30+ day account. Faster review.

✅

Verified

Manual verification + GitHub history. Can submit skills.

🏛️

Official

OpenClaw team or endorsed projects. Instant publish.

Found something suspicious? Every listing has a Report button. 3+ reports trigger automatic quarantine and manual review.