Caveat verdict

bankr

riskagent

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

Accesses credentials AND makes external network calls

Skill ('bankr') executes real cryptocurrency trades, transfers, leveraged positions, and Polymarket bets using wallet credentials on Base/Ethereum/Polygon/Solana; while the service is legitimate, the combination of autonomous financial transactions and wallet private key access represents elevated real-world financial risk.

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.

0
security
40
transparency
70
maintenance

What it does

These are capability combinations: each listed behavior occurs in the skill, but Caveat detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.

Capability combination high

Accesses credentials AND makes external network calls — potential credential theft

LLM02 · ASI03

Permission integrity

Makes network requests but does not declare curl/wget in required binaries

network_out

Code accesses API keys/tokens but declares no environment variables

credential_access

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (6)

Pattern match critical

Possible hardcoded credential

references/llm-gateway.md · code · TOKEN="your_key_here

Pattern match high

Long base64 string (100+ chars) — likely obfuscated payload

references/sign-submit-api.md · code · 0xa9059cbb000000000000000000000000recipient0000000000000000000000000000000000000

Pattern match high

Accesses OpenClaw config/secrets directly

references/llm-gateway.md · code · ~/.openclaw/openclaw.json

Pattern match medium

Accesses shell history/config

references/llm-gateway.md · prose · downgraded · ~/.zshrc

Pattern match low

Opens WebSocket connection

references/agent-profiles.md · prose · downgraded · WebSocket

Pattern match low

Makes HTTP request to external URL

references/sign-submit-api.md · code · fetch('https://

Permissions & capabilities

No declared permissions — minimal attack surface.

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