Caveat verdict

moltbillboard

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

Accesses credentials AND makes external network calls

The skill explicitly enables autonomous agent payments on Base mainnet using USDC without human checkout ('No redirect, no human required'), which constitutes real financial transactions beyond typical safe agent behavior.

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
80
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

Findings (3)

Pattern match critical

<script> tag in markdown — potential code injection

SKILL.md · code · <script

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.

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