Find Skills Skill

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

Overview

This instruction-only skill appears to be a benign guide for finding OpenClaw skills, with the main caution that users should verify any CLI command or third-party skill source before using it.

This skill is safe to treat as a discovery guide, not an installer. If you follow its npx examples or visit third-party marketplaces and GitHub repositories, verify the source and review any skill carefully before installing it.

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.

#
ASI05: Unexpected Code Execution
Low
What this means

If the user follows these examples, a CLI package may run on their machine to search ClawHub.

Why it was flagged

The skill documents user-run npx commands. npx can execute a local or fetched CLI package, which users should run intentionally; however, these examples are disclosed and central to the skill-search purpose.

Skill content
npx clawhub search "keyword"

# Browse categories
npx clawhub browse
Recommendation

Run these commands only when intended, and verify the clawhub CLI/package source if it is not already installed.

#
ASI04: Agentic Supply Chain Vulnerabilities
Low
What this means

Users could discover skills from sources that are less vetted than an official registry.

Why it was flagged

The skill recommends community and GitHub sources for finding installable skills. This is purpose-aligned for discovery, but these sources may have varying provenance and review quality.

Skill content
LobeHub Skills Marketplace
- Website: https://lobehub.com/skills
- Community-contributed skills

### 4. GitHub
- Search: `openclaw skill` or `agent-skill`
Recommendation

Before installing any discovered skill, review its SKILL.md, permissions, source, requirements, and reputation, and test it in isolation as the artifact itself recommends.