ClawAudit verdict

mai

45
🟠 Risky
Significant concerns — only install if you understand the risks

The skill accesses credentials for transaction tracking and registry-backed PSP custody records, which may pose a risk if not handled properly.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

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

35
security
90
transparency
100
maintenance

Findings (6)

Pattern match high

HTTP request to bare IP address — common in malicious payloads

SKILL.md · code · http://127.0.0.1

Pattern match high

Possible hardcoded credential

tests/test_public_marketplace.py · prose · downgraded · token="admin-token

Pattern match medium

References child_process — can spawn system processes

plugins/mai-plugin/openclaw_compat.js · prose · downgraded · child_process

Pattern match medium

subprocess execution — runs system commands from Python

tests/test_install.py · prose · downgraded · subprocess.run(

Pattern match low

Accesses sensitive environment variables

plugins/mai-plugin/openclaw_compat.js · prose · downgraded · process.env.MAI_API_KEY

Pattern match low

Python urllib.request — network access

scripts/mai.py · prose · downgraded · urllib.request

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class B/D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

No declared permissions — minimal attack surface.

credential_access

Is this flag fair?

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