Back to skill
Skillv1.0.0
ClawScan security
Moral Compass · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignFeb 13, 2026, 3:00 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- An instruction-only ethical guidance skill that is internally consistent with its stated purpose and poses low technical risk (no installs, no credentials, no external endpoints).
- Guidance
- This skill is an ethical guidance pack inspired by Bahá'í teachings — technically low-risk because it's instruction-only and asks for no permissions. Consider whether you want an explicitly Bahá'í-informed normative framework applied by your agent (it may decline or reframe requests according to those principles). The source/homepage are unspecified; if provenance or licensing matters for your use case, ask the publisher for attribution or provenance. Test the skill with a few sample dilemmas to ensure its behavior and tradeoffs align with your organizational or personal policies before relying on it in sensitive workflows.
Review Dimensions
- Purpose & Capability
- okThe name/description (an ethical framework inspired by the Bahá'í Writings) matches the content: guidance, principles, and scenario-based advice. Nothing in the bundle requests unrelated privileges or capabilities.
- Instruction Scope
- okSKILL.md and the reference files contain only normative guidance and examples for ethical reasoning. There are no instructions to read system files, access environment variables, call external endpoints, or perform actions outside of producing reasoned responses.
- Install Mechanism
- okNo install spec or code files that would be written to disk or executed. This is an instruction-only skill (lowest install risk).
- Credentials
- okThe skill requires no environment variables, credentials, or config paths — the requested access is minimal and appropriate for an instruction-only ethics guide.
- Persistence & Privilege
- okalways is false, user-invocable is true, and model invocation is allowed (defaults). The skill does not request permanent inclusion, system-wide changes, or access to other skills' configs.