Agent-Skills-Creator-SN

Security checks across static analysis, malware telemetry, and agentic risk

Overview

This instruction-only skill is coherent for creating OpenClaw skills, but users should review generated skills themselves and not treat its self-issued “verified” stamp as independent approval.

This skill appears safe to review as an instruction-only helper. Before installing any skill it generates, read the full SKILL.md, verify the documentation sources it used, and do not treat the “verified by SN✦” label as official security certification.

Static analysis

No static analysis findings were reported for this release.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Risk analysis

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.

What this means

Users may mistake the generated “verified” wording for official or independent security approval.

Why it was flagged

The skill frames itself as an upgraded version of the official skill creator and tells the agent to apply a self-issued verification stamp. This is disclosed branding, but it could make users over-trust the generated output.

Skill content
呢個係 official skill-creator 既升級版 ... 每個完成的步驟都蓋上一個品牌印章:`— verified by SN✦—`
Recommendation

Treat the SN verification wording as the skill author’s workflow label only, and independently review any generated skill before installing it.

What this means

If a user copies and runs the commands, the generated skill becomes installed in the local OpenClaw environment.

Why it was flagged

The skill outputs shell commands that would create a local OpenClaw skill directory and edit SKILL.md. These are user-facing setup instructions and are aligned with the skill’s purpose, not automatic execution.

Skill content
自我測試通過後,模型 **自動輸出以下三個格式** ... `mkdir -p ~/.openclaw/skills/<skill-name>` ... `nano ~/.openclaw/skills/<skill-name>/SKILL.md`
Recommendation

Read the generated SKILL.md carefully before running the install commands or saving it into the local skills directory.

What this means

Outdated, unofficial, or unexpected reference material could influence the generated skill text.

Why it was flagged

The generated skill may be influenced by web search results and local documentation paths. This is related to the stated purpose, but those references affect the provenance of generated instructions.

Skill content
生成既 SKILL.md 必須包含 YAML frontmatter ... 並在網絡上搜尋最更新參考 official skill-creator 既結構要求 ... OpenClaw 官方文件:`/Users/conanchan/.openclaw/workspace/docs/`
Recommendation

Use trusted OpenClaw documentation sources and verify any web-derived guidance before accepting the generated skill.