Shop Car Insurance

Security checks across static analysis, malware telemetry, and agentic risk

Overview

This is a coherent payment/shopping skill, but installing it gives an agent real spending ability through a CreditClaw API key.

Install only if you intentionally want your agent to shop or pay online. Start with ask-for-everything approval, low spending limits, merchant/category restrictions, and a securely stored CREDITCLAW_API_KEY.

Static analysis

No static analysis findings were reported for this release.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Risk analysis

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

The agent may be able to spend money or start purchases without a separate approval for every transaction if the owner has configured an allowance.

Why it was flagged

The skill can initiate real merchant checkout transactions, including auto-approved transactions within owner-set limits.

Skill content
If the amount is within your auto-approved allowance, it processes immediately
Recommendation

Keep approval mode strict at first, set low limits, review allowed merchants/categories, and require explicit user confirmation before each purchase.

What this means

Anyone who gets the API key could potentially use the configured wallet/card permissions to make charges.

Why it was flagged

The required CREDITCLAW_API_KEY is a sensitive financial credential tied to spending authority.

Skill content
Your API key is your identity. Leaking it means someone else can spend your owner's money.
Recommendation

Store the API key securely, restrict it to this skill, rotate it if exposed, and verify requests only go to https://creditclaw.com/api/.

What this means

Future remote file changes could alter the instructions the agent reads if the user re-downloads them.

Why it was flagged

The optional local setup downloads remote skill documents without checksums or version pinning, though no executable code is shown.

Skill content
curl -s https://creditclaw.com/creditcard/skill.md > ~/.creditclaw/skills/creditcard/SKILL.md
Recommendation

Prefer the reviewed registry copy, or manually review downloaded files from creditclaw.com before use.

What this means

Financial status and spending rules may remain in the agent context for a short time and influence later actions.

Why it was flagged

The skill asks the agent to retain wallet status, spending permissions, balances, and owner notes temporarily for later purchase decisions.

Skill content
Cache this response for up to 30 minutes. Check it before any purchase.
Recommendation

Do not store wallet status longer than needed, avoid sharing it in unrelated conversations, and re-check permissions before purchases.

What this means

If scheduled, the agent may continue polling wallet status periodically even outside a single purchase task.

Why it was flagged

The skill suggests recurring operational checks, but the routine is documented and limited to wallet/status monitoring and guarded top-up requests.

Skill content
CreditClaw Heartbeat (suggested: every 30 minutes)

Run this routine periodically
Recommendation

Only enable periodic checks if you want ongoing monitoring, and ensure top-up requests or purchases still require user approval.