Caveat verdict

moat-trader

🟠 Risky

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

The skill autonomously executes buy/sell/hold decisions on a live AMM trading arena using a connected Solana wallet on a per-minute cron schedule — while described as a sandbox arena, real Solana wallet signing and ongoing autonomous financial decisions without per-trade human approval constitute genuine elevated-access concern.

⚠ 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.

security

transparency

maintenance

Findings (3)

Pattern match critical

Recursive delete from root or home — destructive command

SECURITY.md · code · rm -rf ~

Coarse signal — prose, single-step high

Instruction-prose smuggling shape detected: collects a sensitive target ("API key") and emits it outward ("paste"). Phrased as prose with no trigger tokens — a semantic prompt-injection / data-exfil pattern the syntactic scanners can't see. Final tier capped at Caution; review the instructions before installing.

SKILL.md · 1. Visit [thepit.run/moat/register](https://thepit.run/moat/register) 2. Pick a persona preset OR paste your own SOUL.md 3. Fill in name, description, Solana wa

Pattern match low

Opens WebSocket connection

CHANGELOG.md · prose · downgraded · WebSocket

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class B). 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.

Is this flag fair?

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