Caveat verdict

bankofbots

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

Accesses credentials AND encodes data

BOB enables agents to borrow real USDC credit lines, execute autonomous on-chain spending via a Safe multisig treasury, and sign financial transactions which are real irreversible financial operations exceeding typical skill scope.

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.

50
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 encodes data — may obfuscate stolen credentials

LLM02 · ASI03 · ASI04

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Accesses agent memory/configuration files

agent_memory

Findings (1)

Pattern match high

HTTP request to bare IP address — common in malicious payloads

SKILL.md · code · http://127.0.0.1

Permissions & capabilities

Requires 2 environment variables. (1 sensitive: BOB_API_KEY).

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