Caveat verdict

agentwallet-cli

🟠 Risky

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

Accesses credentials AND encodes data

Core function is generating and using real EVM and Solana private keys for non-custodial smart wallets with onchain spending; while strong safety warnings are present, the skill manages live crypto key material with real financial exposure.

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

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

Code accesses API keys/tokens but declares no environment variables

credential_access

Findings (2)

Confirmed in code medium

Accesses process.env — reads environment variables

SKILL.md · code

Pattern match medium

Accesses sensitive environment variables

SKILL.md · code · process.env.AGENT_PRIVATE_KEY

Permissions & capabilities

No declared permissions — minimal attack surface.

credential_accessdata_encoding

I installed anyway

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