Monzo

AdvisoryAudited by Static analysis on Apr 30, 2026.

Overview

No suspicious patterns detected.

Findings (0)

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

If the agent misunderstands a request or is prompted ambiguously, it could move money between your current account and pots without a second review step.

Why it was flagged

The script directly changes Monzo pot balances using a supplied amount. The provided pot script does not show a confirmation prompt, dry-run, or amount limit before making the banking API call.

Skill content
response=$(monzo_api_call PUT "/pots/$POT_ID/deposit" ... -d "amount=$AMOUNT" ...)
response=$(monzo_api_call PUT "/pots/$POT_ID/withdraw" ... -d "amount=$AMOUNT" ...)
Recommendation

Require explicit confirmation that repeats the exact account, pot, direction, and amount before any deposit or withdrawal. Consider a read-only default mode or an allowlist for write operations.

What this means

Anyone who can access the encrypted file and the keyring password may be able to use your Monzo API connection.

Why it was flagged

The skill stores persistent delegated Monzo credentials. This is expected for the integration and is documented as encrypted, but it grants ongoing banking account access if the local password or machine is compromised.

Skill content
The following are stored in the encrypted credentials file:
- OAuth Client ID and Client Secret
- Access Token and Refresh Token
- Default Account ID
Recommendation

Use a strong unique MONZO_KEYRING_PASSWORD, keep config files private, run only on a trusted machine, and revoke the connected app in Monzo if you stop using the skill.

What this means

A webhook pointed at the wrong endpoint could send transaction notifications to someone else.

Why it was flagged

The webhook feature can create a persistent external data flow containing transaction notifications. The risk is disclosed and HTTPS is required, but endpoint ownership cannot be verified by the skill.

Skill content
Webhooks — Register and manage real-time transaction webhooks ... Only point webhooks at endpoints you control. An attacker-controlled webhook would receive your transaction notifications.
Recommendation

Only create webhooks for endpoints you control, confirm the URL carefully before registration, and periodically list/delete old webhooks.

What this means

You have less external provenance to rely on when deciding whether to trust this banking integration.

Why it was flagged

The skill has a provenance gap. That is especially important because it handles banking credentials and account access, even though the provided code is visible and the static scan was clean.

Skill content
Source: unknown
Homepage: none
Recommendation

Review the included scripts before use and prefer installing banking-related skills from maintainers and repositories you can verify.