ClawAudit verdict

pumpclaw-agent

45
๐ŸŸ  Risky
Significant concerns โ€” only install if you understand the risks

PumpClaw Agent skill generates customer-ready Telegram polling bots and Express-style web servers for tokenized agent payments, interacting with financial transactions and requiring elevated access.

โš  Flagged for review โ€” coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis โ€” not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

70
security
90
transparency
70
maintenance

Findings (2)

Pattern match high

HTTP request to bare IP address โ€” common in malicious payloads

assets/template/README.md ยท code ยท http://127.0.0.1

Pattern match medium

Uses exec() โ€” may execute shell commands

assets/template/src/server.js ยท prose ยท downgraded ยท exec(

Permissions & capabilities

No declared permissions โ€” minimal attack surface.

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API