Caveat verdict

stripe

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

Accesses credentials AND makes external network calls

CreditClaw enables AI agents to accept card details and make real purchases across many e-commerce platforms with owner approval as the only gate; the broad purchase capability and real-money transaction scope for an autonomous agent represents genuine 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
60
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

Findings (3)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · API_KEY="cck_live_7f3e...

Pattern match high

<script> tag in markdown — potential code injection

shopify/SHOPIFY.md · prose · downgraded · <script

Pattern match medium

References webhook/callback URL

MANAGEMENT.md · code · callback_url

Permissions & capabilities

Requires 1 environment variable. (1 sensitive: CREDITCLAW_API_KEY).

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