ClawAudit verdict

Prediction Stack Setup

prediction-stack-setup

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

The setup wizard configures cron-based autonomous market scanning and trade alert jobs using Anthropic API keys, Kalshi trading credentials, and iMessage delivery, wiring a trading system that operates without per-action user approval.

⚠ 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.

23
security
50
transparency
70
maintenance

Permission integrity

Code accesses API keys/tokens but declares no environment variables

credential_access

Findings (4)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · API_KEY="sk-ant-...

Pattern match high

Instructs covert action — may act without user awareness

SKILL.md · code · silently

Pattern match medium

Python os.getenv — reads environment variable

references/validation-troubleshooting.md · code · os.getenv(

Pattern match low

POSTs data to external URL

scripts/validate_setup.py · prose · downgraded · .post( "http://

Permissions & capabilities

No declared permissions — minimal attack surface.

credential_accessnetwork_in

Is this flag fair?

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