Startup Verifier
PassAudited by VirusTotal on May 2, 2026.
Overview
Type: OpenClaw Skill Name: startup-verifier Version: 2.1.0 The skill bundle consists of a metadata file and a set of Markdown instructions (SKILL.md) for evaluating startup ideas for the Russian market. The instructions define a 14-point evaluation framework and scoring logic (Green/Yellow/Red) based on criteria like market competition, MVP development speed, and payment viability. There is no executable code, no evidence of data exfiltration, and no malicious prompt injection intended to subvert the agent's behavior.
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.
Startup details or research queries may be shared with external services, and untrusted external results could affect the GREEN/YELLOW/RED verdict.
The skill directs the agent to rely on another agent/service and an MCP API, and elsewhere to cross-check with external web sources. This is aligned with the market-research purpose, but the artifacts do not define the identity, permissions, or data-handling boundaries of those external integrations.
Получить результаты от **Стратега** и **idea-reality-mcp API**
Use trusted external sources, avoid sending confidential startup information unless appropriate, and review cited evidence before acting on the verdict.
Users may have less clarity about exactly which documented version they are installing, but no hidden executable behavior is shown.
The provided registry metadata lists version 2.1.0 while _meta.json lists 1.0.0 and SKILL.md labels the verifier as v2.0. Because there is no code or install mechanism, this is only a release/provenance clarity issue.
"version": "1.0.0"
Confirm the registry listing is the intended current release before relying on the skill for repeatable evaluations.