Real Skill packageSource verifiedClawHub registry

Universal Agent

This skill should be used when the user needs to execute tasks through a complete automated workflow: understand natural language intent, dynamically generat...

Identity and source

Publisher attribution波动几何registry owner unverified by skillvetai
Functional categoryAgent Engineering, Security & Governanceautomatically inferred · 60% rule confidence
Package forminstruction with code5 recorded files
Canonical sourceClawHub registryclawhub:wangjiaocheng:universal-agent
Open canonical source ↗

Platform declarations

These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.

OpenClawnative officialProvenance: registry distribution

Independent structural checks

These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.

Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 9/10/2026.claude/skills/universal-agent

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenAI Codexpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 9/10/2026.agents/skills/universal-agent

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenClawpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+openclaw-docs-2026-08-13 · 9/10/2026skills/universal-agent

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

Installation and inspection

This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.

clawhub install @wangjiaocheng/universal-agent
clawhub inspect @wangjiaocheng/universal-agent --version 1.0.0

Security evidence

SkillVetAI static result: high signal

This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.

Status
completed
Coverage
full text content
Files
5 / 5 inspected as text
Checked
9/10/2026, 4:44:41 AM
Scanner
0.1.3
Policy
1.0.3
3 automated findings
highRemote content is piped directly to a shellreferences/README.md:248 · confidence 98%curl -fsSL https://ollama.ai/install.sh | sh
highDynamic code or shell execution is presentscripts/universal_agent.py:943 · confidence 78%eval(
mediumRemote installer is downloaded without an integrity checkreferences/README.md:248 · confidence 70%curl -fsSL https://ollama.ai/install.sh
2 High/Critical review queue entries
STATIC_DOWNLOAD_PIPE_TO_SHELLpending
STATIC_DYNAMIC_CODE_EXECUTIONpending
Open human review queue →
5 inferred permission indicators
  • shell execution — automatically inferred
  • network access — automatically inferred
  • filesystem read — automatically inferred
  • filesystem write — automatically inferred
  • credential access — automatically inferred
6 dependency and API indicators
  • api: api.groq.com
  • api: api.openai.com
  • api: clawhub.ai
  • api: dashscope.aliyuncs.com
  • api: ollama.ai
  • api: open.bigmodel.cn
External clawhub result: suspicious

This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.

Evidence checked
5/29/2026, 9:31:51 PM
Release binding
Matches this record
  • vt: clean
  • skillspector: suspicious
  • llm: suspicious

Recorded files

The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.

Package content hashsha256:2a7cd510ab98f3d1b420c4e5ee372eb02e24c34ed0967b808a697570b894a3c9
Show up to 5 recorded paths
  • references/README.md
  • scripts/config.json
  • scripts/universal_agent.py
  • skill-card.md
  • SKILL.md

Source changelog

Universal Agent 1.0.0 – Initial Release - Introduces a minimal universal agent that automates end-to-end task execution from natural language input, including command/script generation, execution, error recovery, and result summarization. - Provides standalone, bridge, and inline simulation usage modes to suit various integration scenarios. - Supports shell commands, Python scripting, API/API calls, CLI tools, and basic hardware control. - Features auto-retry on error and safety checks to ensure reliable automation workflows. - Includes detailed protocol for external agent integration (environment variables) and full file structure/documentation.