Caveat verdict

agent-fuel

45
🟠 Risky
Significant risk patterns flagged — automated deep scan, not behavioral proof.

Skill autonomously executes real financial transactions (buying USDC via MoonPay CLI) and manages crypto wallet balances without per-transaction human approval, which constitutes real financial risk; the auto top-up logic can spend real money up to a daily limit autonomously.

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

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

73
security
80
transparency
80
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (3)

Pattern match medium

Instructs covert action — may act without user awareness

README.md · prose · downgraded · silently

Pattern match medium

References child_process — can spawn system processes

src/monitor.ts · prose · downgraded · child_process

Pattern match low

Popular HTTP library — network access

README.md · prose · downgraded · got

Why the tier is capped

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

Permissions & capabilities

Requires 1 system binary.

package_install

Is this flag fair?

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