Real Skill packageSource verifiedClawHub registryAutomatic security hold

ai-company

Micro-tier governance skill for small AI agent organizations (1-3 agents). Consolidates 18 enterprise function blocks into two departments, governance-and-delivery and engineering-and-safety, covering strategy, risk, compliance, architecture, safety, and delivery. Ships ten harness code templates, three prompt frameworks, a full error-code catalog, and a scaling specification. Provides two self-contained human-paste prompts (method implementation, robustness checks) usable in any AI chat window. Source files are a…

Identity and source

Publisher attributionJohnSmithfanregistry owner unverified by skillvetai
Functional categoryEnterprise Functionsautomatically inferred · 62% rule confidence
Package forminstruction with code26 recorded files
Canonical sourceClawHub registryclawhub:johnsmithfan:ai-company
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 · 9/23/2026.claude/skills/ai-company

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 · 9/23/2026.agents/skills/ai-company

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 · 9/23/2026skills/ai-company

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

Installation and inspection

Installation commands are hidden while this fixed release is under an automatic security hold. Review the evidence and canonical source manually.

Security evidence

SkillVetAI static result: critical 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
25 / 26 inspected as text
Checked
9/23/2026, 1:28:05 PM
Scanner
0.1.3
Policy
1.0.3
2 automated findings
criticalDestructive command targets a system roottests/test-method-patterns.py:335 · confidence 98%rm -rf /
highDynamic code or shell execution is presenttests/test-method-patterns.py:246 · confidence 78%exec(
2 High/Critical review queue entries
STATIC_DESTRUCTIVE_ROOT_COMMANDpending
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
9 dependency and API indicators
  • api: clawhub.ai
  • api: fsf.org
  • api: github.com
  • api: img.shields.io
  • api: keepachangelog.com
  • api: semver.org
  • api: www.contributor-covenant.org
  • api: www.conventionalcommits.org
  • api: www.gnu.org
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
9/22/2026, 12:35:25 AM
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:a36f566dfc656e8ff784b51e228c7a721883545363bb78fe403865fd3fa2e345
Show up to 26 recorded paths
  • _meta.json
  • .editorconfig
  • .gitignore
  • .scaling-state.json
  • AGENTS.md
  • CHANGELOG.md
  • CODE_OF_CONDUCT.md
  • CONTRIBUTING.md
  • LICENSE
  • prompts/01-implement-method.md
  • prompts/02-robustness-checks.md
  • README-FOR-AI.md
  • README.en.md
  • README.md
  • README.zh.md
  • references/departments/engineering-and-safety.md
  • references/departments/governance-and-delivery.md
  • references/error-codes.md
  • references/method-patterns.md
  • references/scaling.md
  • scripts/scaling-config.json
  • scripts/self-scale.ps1
  • SECURITY.md
  • skill-card.md
  • SKILL.md
  • tests/test-method-patterns.py

Source changelog

ai-company v0.1.0 changelog: - Major redesign: Now a micro-tier governance skill for small AI agent organizations (1–3 agents), consolidating 18 enterprise functions into two departments. - Ships 10 shared harness code templates, 3 prompt frameworks, a complete error code catalog, and a full scaling specification. - Includes two human-paste prompts for method implementation and robustness checks, usable in any AI chat window. - Supports propose-only self-scaling with up-to-group tier evaluation and upgrade proposals. - Source files authored in English; runtime output follows user language with English fallback, per language policy. - Extensive cleanup: removed former docs, examples, and implementation guides; now focused on governance, engineering harness, compliance, PII masking, and traceable agent operation.