Back to skill
Skillv1.0.0
ClawScan security
Creative Genius · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignFeb 27, 2026, 4:45 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is an instruction-only creativity coaching skill; it contains no code, does not request credentials or system access, and its requirements and instructions match the stated purpose.
- Guidance
- This skill is an instruction-only creativity guide and appears internally consistent and low-risk: it neither installs code nor requests credentials. Before enabling autonomous invocation in an agent, consider whether you want the agent to act on creative prompts without human review (the skill could suggest actions or ask for user input). If you want stricter control, keep the skill user-invocable only and review outputs before they are executed or shared.
Review Dimensions
- Purpose & Capability
- okName and description promise methods for creative thinking; the SKILL.md contains detailed, relevant techniques and workflows from historical figures and nothing that contradicts or exceeds that purpose.
- Instruction Scope
- okThe runtime instructions are purely prescriptive guidance (techniques, routines, workflows). They do not instruct the agent to read files, access environment variables, call external endpoints, or collect system data.
- Install Mechanism
- okNo install spec or code files are present; this is instruction-only so nothing is downloaded or written to disk.
- Credentials
- okThe skill declares no required environment variables, credentials, or config paths — consistent with an education/coaching skill that only supplies methods and prompts.
- Persistence & Privilege
- okalways is false and model invocation is not disabled (normal). The skill does not request permanent presence or elevated privileges.