Back to skill
Skillv1.0.0
ClawScan security
Nubank · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 29, 2026, 11:05 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is an instruction-only informational skill about Nubank (a digital bank); it has no install steps, no requested credentials, and its runtime instructions are limited to providing background content — the pieces are coherent.
- Guidance
- This skill is a static informational card about Nubank and poses minimal technical risk. Before installing, consider that the source and homepage are not provided — if you plan to rely on this for financial decision-making, prefer skills from verifiable authors or with citations. Never supply account credentials or sensitive personal data to an informational skill; if the skill later asks for authentication or access to accounts, treat that as a red flag.
Review Dimensions
- Purpose & Capability
- okName, description, and SKILL.md all describe an informational reference card about Nubank. The skill declares no binaries, env vars, or config paths — consistent with a read-only knowledge card.
- Instruction Scope
- okSKILL.md contains static company background, timeline, business model, and read_when triggers for when to include the card. It does not instruct the agent to read files, access environment variables, call external endpoints, or exfiltrate data.
- Install Mechanism
- okNo install spec and no code files are present (instruction-only). Nothing is written to disk and there are no external downloads.
- Credentials
- okThe skill requests no environment variables, credentials, or configuration paths — appropriate for a purely informational skill.
- Persistence & Privilege
- okalways is false and the skill is user-invocable (normal). It does not request persistent presence or modify other skill/system settings.