Skillv1.0.0

ClawScan security

Ing Bank · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

BenignApr 26, 2026, 11:02 AM

Verdict: benign
Confidence: high
Model: gpt-5-mini
Summary: This is an informational, instruction-only skill about ING Group with no installs, no required credentials, and no unexpected behaviors — it's coherent with its stated purpose.
Guidance: This skill is informational only and appears low-risk: it contains a static overview of ING and asks for no installs, credentials, or filesystem access. The only minor concern is that the package source/homepage is 'unknown' — if you prefer provenance, look for an official or well-documented source before trusting it. Do not use this skill to perform transactions or to submit any secrets; if future versions add env vars, network calls, or install steps, re-evaluate before enabling.}

Purpose & Capability: okThe skill's name/description and the SKILL.md content match: it's an informational profile of ING Bank. It declares no binaries, env vars, or config paths, which is appropriate for a read-only reference skill.
Instruction Scope: okSKILL.md contains only summary text and 'read_when' contexts for when to present the content. It does not instruct the agent to read files, access environment variables, call external endpoints, or perform actions beyond providing information.
Install Mechanism: okThere is no install spec and no code files. Nothing will be written to disk or executed as part of installing this skill.
Credentials: okThe skill requests no environment variables or credentials, which is proportionate for an informational description of a bank.
Persistence & Privilege: okalways is false and the skill does not request elevated or persistent privileges. Autonomous invocation is allowed (platform default) but this skill's actions are read-only text presentation.