Back to skill
Skillv1.0.0
ClawScan security
Mvp · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 7, 2026, 11:09 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is an instruction-only business-advice skill (MVP guidance) that asks for no credentials, installs nothing, and its runtime instructions stay on-topic for the stated purpose.
- Guidance
- This skill is an instruction-only advisor for building MVPs and does not request credentials or install code, so its scope and requirements are coherent with its description. Before relying on any business advice: verify critical decisions (pricing, legal, taxes) with domain experts, avoid sharing sensitive account credentials or proprietary data in prompts, and treat the output as guidance rather than definitive professional advice. If you prefer no autonomous invocations, disable model invocation for skills in your agent settings.
Review Dimensions
- Purpose & Capability
- okThe name and description match the SKILL.md content: the skill provides minimalist MVP guidance. It requests no binaries, env vars, or config paths — all of which are appropriate and proportionate for a purely advisory skill.
- Instruction Scope
- okSKILL.md contains concrete, scoped instructions for advising on MVP scope, manual→process→product stages, and an output checklist. It does not instruct the agent to read files, access environment variables, or transmit data to external endpoints beyond providing advice to the user.
- Install Mechanism
- okNo install specification or code files are present (instruction-only). Nothing is downloaded or written to disk, which minimizes risk.
- Credentials
- okThe skill requires no environment variables, credentials, or config paths. There is no disproportionate request for secrets or unrelated access.
- Persistence & Privilege
- okalways is false (not force-included) and the skill does not request or modify other skills or system-wide settings. It allows normal autonomous invocation by the agent (platform default), which is expected for an invocable skill.