AI Agent Blacklist
After scanning 96,096 skills,
ATR flagged 1,302 with risks.
552 confirmed as malware.
This list is fully public. Anyone can check.
A 100%-malicious publisher on OpenClaw distributing 354 poisoned skills disguised as cryptocurrency and Google Workspace tools. Uses password-protected archives and paste services to bypass automated scanning.
The most technically direct actor of the three. Ships skills with base64-encoded curl-to-bash payloads that call back to C2 server 91.92.242.30 for arbitrary command execution.
Targets Chinese-speaking developers with business-tool skill disguises. Mixes malicious and benign skills (72% malicious) as a credibility-building and removal-evasion strategy.
These skills passed ATR's 113-rule scan
with zero CRITICAL / HIGH findings.
Safe to use.
Every flagged skill lives in the public blacklist.json. Any CI, registry, or agent framework can pull it directly.
This list is generated from ATR ecosystem scans
and synced with Threat Cloud.
Being flagged does not guarantee malice —
check the specific rules for risk assessment.
Report false positives via GitHub Issues.