Back to skill
Skillv1.0.0
ClawScan security
Brainstorm Facilitator · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 29, 2026, 4:32 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill is an instruction-only brainstorming assistant that only needs user-provided brief data and its instructions match the described Six Hats methodology — there are no installs, credentials, or suspicious behaviors.
- Guidance
- This skill appears internally consistent and low-risk: it only follows a structured brainstorming procedure and asks for user-provided brief details. Before using it, avoid pasting secrets or private data into the brief (API keys, full customer records, internal credentials). Treat its outputs as creative guidance — verify legal, regulatory, or safety implications yourself before acting, and watch for hallucinated facts or unsupported claims in proposed concepts.
Review Dimensions
- Purpose & Capability
- okName and description (Six Hats brainstorming producing three concepts) match the SKILL.md instructions exactly; no unrelated capabilities or external services are requested.
- Instruction Scope
- okRuntime instructions are limited to framing the brief, running the six-hat thinking process, synthesizing three concepts, and scoring them. There are no directives to read system files, environment variables, network endpoints, or to exfiltrate data.
- Install Mechanism
- okNo install spec and no code files — instruction-only. Nothing will be written to disk or downloaded during install.
- Credentials
- okThe skill declares no required environment variables, credentials, or config paths. User input (theme, constraints, etc.) is the only data it needs.
- Persistence & Privilege
- okalways is false and the skill is user-invocable (normal). It does not request persistent presence, system-level changes, or access to other skills' configs.