Real Skill packageSource verifiedClawHub registry

JEP Guard

Configure or inspect a local execution policy gate when the user requests JEP Guard protection.

Identity and source

Publisher attributionJEP (Judgment Event Protocol)registry owner unverified by skillvetai
Functional categoryEnterprise Functionsautomatically inferred · 56% rule confidence
Package forminstruction with code128 recorded files
Canonical sourceClawHub registryclawhub:schchit:jep-guard
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 · 9/17/2026.claude/skills/jep-guard

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 · 9/17/2026.agents/skills/jep-guard

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 · 9/17/2026skills/jep-guard

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 @schchit/jep-guard
clawhub inspect @schchit/jep-guard --version 3.0.0

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
partial text content
Files
40 / 128 inspected as text
Checked
9/17/2026, 4:50:34 AM
Scanner
0.1.3
Policy
1.0.3
1 automated finding
highEncoded content is decoded and executed__tests__/security.test.ts:20 · confidence 90%base64
1 High/Critical review queue entry
STATIC_OBFUSCATED_EXECUTIONpending
Open human review queue →
4 inferred permission indicators
  • network access — automatically inferred
  • filesystem read — automatically inferred
  • filesystem write — automatically inferred
  • credential access — automatically inferred
8 dependency and API indicators
  • npm: commander 12.1.0
  • npm: inquirer 8.2.7
  • npm: tweetnacl 1.0.3
  • npm: canonicalize 2.1.0
  • npm: openclaw >=1.0.0
  • api: clawhub.ai
  • api: github.com
  • api: jep.local
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
9/17/2026, 2:10:05 AM
Release binding
Matches this record
  • vt: clean
  • skillspector: suspicious
  • llm: clean

Recorded files

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

Package content hashsha256:47e06f640c4ea5c1c6d79b13f37f2dc4087f7dcb0988d2ee613109f034ce5e5c
Show up to 30 recorded paths
  • __tests__/jep-core.test.ts
  • __tests__/security.test.ts
  • bin/jep-guard
  • BUILD-INFO.json
  • dist/cli/commands/daemon.d.ts
  • dist/cli/commands/daemon.js
  • dist/cli/commands/daemon.js.map
  • dist/cli/commands/dashboard.d.ts
  • dist/cli/commands/dashboard.js
  • dist/cli/commands/dashboard.js.map
  • dist/cli/commands/delegate.d.ts
  • dist/cli/commands/delegate.js
  • dist/cli/commands/delegate.js.map
  • dist/cli/commands/export.d.ts
  • dist/cli/commands/export.js
  • dist/cli/commands/export.js.map
  • dist/cli/commands/init.d.ts
  • dist/cli/commands/init.js
  • dist/cli/commands/init.js.map
  • dist/cli/commands/judge.d.ts
  • dist/cli/commands/judge.js
  • dist/cli/commands/judge.js.map
  • dist/cli/commands/skills.d.ts
  • dist/cli/commands/skills.js
  • dist/cli/commands/skills.js.map
  • dist/cli/commands/status.d.ts
  • dist/cli/commands/status.js
  • dist/cli/commands/status.js.map
  • dist/cli/commands/terminate.d.ts
  • dist/cli/commands/terminate.js

Source changelog

Major v3.0.0 release with significant architecture and policy changes: - Rewrote documentation and usage guidance in SKILL.md to focus on local execution and explicit operator control. - External kernel integrations and cross-skill forwarding are now disabled. - Full mode now allows only authenticated, policy-approved requests with valid bound capabilities; passive mode does not protect execution. - Audit storage is strictly local; operator is responsible for securing and archiving logs. - Integration hooks, background service management, and state changes are no longer automatic—explicit operator action is required. - Added many new files including tests, CLI commands, documentation, and build info. Removed legacy skill card/markdown files.