Back to skill
Skillv1.0.0
ClawScan security
Archer Daniels Midland · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 30, 2026, 1:07 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is an instruction-only informational skill about the company Archer Daniels Midland (ADM); it requests no credentials, installs nothing, and its instructions are limited to presenting corporate/background information.
- Guidance
- This skill is informational and appears coherent with its stated purpose. It does not ask for credentials or install code, so it is low-risk to enable. However, the source is 'unknown' and there is no homepage or citation list — if you need authoritative or up-to-date corporate data (financials, filings, or regulatory history), cross-check with official sources (company site, SEC filings, reputable news or industry reports) before acting on the information provided.
Review Dimensions
- Purpose & Capability
- okThe skill's name and description match the SKILL.md content (company history, business analysis, facts). Nothing in the package asks for unrelated capabilities or resources.
- Instruction Scope
- okSKILL.md contains only descriptive content and a short 'read_when' list indicating when to present this information. It does not direct the agent to read files, access environment variables, call external endpoints, or collect user data.
- Install Mechanism
- okNo install spec and no code files are present. This instruction-only skill writes nothing to disk and executes no installs, which is the lowest-risk model.
- Credentials
- okThe skill declares no required environment variables, credentials, or config paths. There is no disproportionate request for secrets or system access.
- Persistence & Privilege
- okalways is false, the skill is user-invocable and may be invoked autonomously per platform defaults, but it does not request elevated or persistent system privileges or modify other skills.