Real Skill packageSource verifiedClawHub registry

TinkerClaw Shell Security

Classify every shell command as SAFE, WARN, or CRIT before your agent runs it. The classification is instruction-only and runs nothing. The package also ships optional installer scripts that MODIFY SOURCE CODE in an OpenClaw checkout you point them at — they refuse non-OpenClaw trees, verify the whole edit in a temp file before touching the real one, back up, require --yes, offer --dry-run, never rebuild unless you ask, and ship with an unpatch off-switch that validates its range instead of deleting between marker…

Identity and source

Publisher attributionOscar Serraregistry owner unverified by skillvetai
Functional categoryAgent Engineering, Security & Governanceautomatically inferred · 63% rule confidence
Package forminstruction with code8 recorded files
Canonical sourceClawHub registryclawhub:globalcaos:shell-security-ultimate
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 · 9/9/2026.claude/skills/shell-security-ultimate

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 · 9/9/2026.agents/skills/shell-security-ultimate

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 · 9/9/2026skills/shell-security-ultimate

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 @globalcaos/shell-security-ultimate
clawhub inspect @globalcaos/shell-security-ultimate --version 2.3.2

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
8 / 8 inspected as text
Checked
9/9/2026, 4:42:48 PM
Scanner
0.1.3
Policy
1.0.3
3 automated findings
highRemote content is piped directly to a shellSKILL.md:21 · confidence 98%curl | bash
highDynamic code or shell execution is presentSKILL.md:102 · confidence 78%exec (
mediumWorld-writable permissions are requestedSKILL.md:33 · confidence 95%chmod 777
2 High/Critical review queue entries
STATIC_DOWNLOAD_PIPE_TO_SHELLpending
STATIC_DYNAMIC_CODE_EXECUTIONpending
Open human review queue →
3 inferred permission indicators
  • shell execution — automatically inferred
  • network access — automatically inferred
  • filesystem write — automatically inferred
3 dependency and API indicators
  • api: clawhub.ai
  • api: evil.example
  • api: github.com
External clawhub result: clean

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
9/9/2026, 8:34:31 AM
Release binding
Matches this record
  • vt: clean
  • skillspector: clean
  • llm: clean

Recorded files

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

Package content hashsha256:bdd874b6ccf43b513160297d560ec505bd854f89007d631bd377209c591440de
Show up to 8 recorded paths
  • _meta.json
  • scripts/cmd_display.py
  • scripts/patch-openclaw.sh
  • scripts/unpatch-openclaw.sh
  • skill-card.md
  • SKILL.md
  • tests/test_cmd_display.py
  • tests/test_patch_roundtrip.sh

Source changelog

Sanitize terminal output; verify patch/unpatch on a temp file before writing; stop overclaiming command blocking.

Release security diff

highCompared fixed releases 2.3.1 and 2.3.2; 0 finding and 1 permission indicators were added.

Both fixed releases were scanned under the current scanner and policy, so finding, permission and dependency changes are available.

Permission escalation detected
Change reasons and limitations
  • new sensitive permission
  • permission surface changed
  • dependency surface changed
  • file surface changed
  • content hash changed

Observed release history

These older immutable releases were observed by prior successful syncs. They remain recorded when a newer release becomes current.

2.3.19/7/2026sha256:ab5b2d239d9f6728d9d33eea521933b90962fd3184d547a535fe44b81d5e3ba0