MVP
PassAudited by VirusTotal on May 12, 2026.
Overview
Type: OpenClaw Skill Name: mvp Version: 1.0.0 The skill bundle consists entirely of markdown files providing guidance on MVP development. There are no executable scripts, no external network requests, no attempts at prompt injection against the AI agent, and no instructions for the agent to perform any actions beyond processing and presenting the provided information. All content is purely informational and aligns with the stated purpose.
Findings (0)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
If used carelessly, the advice could lead to misleading early users about how a product works or how their data is handled.
The guide recommends a common MVP validation technique where users may believe a process is automated when it is manual. This is purpose-aligned product advice, but it can create trust or disclosure issues if followed literally.
Wizard of Oz 1. Build the UI/interface 2. You manually do the work behind the scenes 3. User thinks it's automated
Use fake-door and Wizard-of-Oz tests with clear early-access language, avoid false claims, and disclose manual processing where privacy, payment, or user expectations could be affected.
Role-specific guidance may fail to load or may require manual navigation if the skill runtime expects the referenced paths exactly.
The role table references files under a roles/ directory, but the provided manifest lists the role files at the package root, such as technical.md and pm.md. This is a coherence/package-path issue, not evidence of malicious behavior.
| Technical Founder | Scope control, stop over-engineering | `roles/technical.md` |
Correct the references to the packaged file paths or move the files into the referenced roles/ directory.