Real Skill packageSource verifiedClawHub registry

untrusted-code-safety

Zero-trust procedure for reviewing or running code from an unknown source. Use when reviewing, vetting, cloning, installing, or running code from an untrusted source (repo invites, packages, scripts, executable config files), when asked whether code is safe or hazardous, when executed code may read secrets/files or reach the network, and when the user says "raise hands", "stop and alert", or "sandbox it". Also trigger on suspicion of malicious, harmful, deceptive, cheating, or stealing behavior.

Identity and source

Publisher attributionJeff Yangregistry owner unverified by skillvetai
Functional categoryAgent Engineering, Security & Governanceautomatically inferred · 63% rule confidence
Package forminstruction bundle2 recorded files
Canonical sourceClawHub registryclawhub:j3ffyang:untrusted-code-safety
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 · 9/29/2026.claude/skills/untrusted-code-safety

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 · 9/29/2026.agents/skills/untrusted-code-safety

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 · 9/29/2026skills/untrusted-code-safety

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 @j3ffyang/untrusted-code-safety
clawhub inspect @j3ffyang/untrusted-code-safety --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
2 / 2 inspected as text
Checked
9/29/2026, 6:09:17 PM
Scanner
0.1.3
Policy
1.0.3
2 automated findings
highRemote content is piped directly to a shellSKILL.md:74 · confidence 98%curl|sh
highEncoded content is decoded and executedSKILL.md:66 · confidence 90%atob
2 High/Critical review queue entries
STATIC_DOWNLOAD_PIPE_TO_SHELLpending
STATIC_OBFUSCATED_EXECUTIONpending
Open human review queue →
4 inferred permission indicators
  • shell execution — automatically inferred
  • network access — automatically inferred
  • filesystem write — automatically inferred
  • credential access — automatically inferred
3 dependency and API indicators
  • api: clawhub.ai
  • api: hackerone.com
  • api: support.github.com
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
9/29/2026, 2:50:20 PM
Release binding
Matches this record
  • 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 hashsha256:6a9dc1f5aa32f8c26c28864dfe7409cd706c6ea4d3cbd8f088f789ea293ef6b5
Show up to 2 recorded paths
  • skill-card.md
  • SKILL.md

Source changelog

Initial release introducing a comprehensive zero-trust workflow for reviewing and running untrusted code. - Defines strict boundaries: only `/tmp` is accessible; no access to personal files, secrets, or network by default. - Provides clear criteria and hard-stop triggers for suspicious activities ("raise hands" procedure). - Outlines a stepwise review and containment procedure: static triage, sensitivity assessment, sandboxed execution, and cleanup. - Supplies practical detection, provenance, and containment recipes for common scenarios (package, repo, scripts). - Includes alerting and instrumentation patterns to monitor and block unsafe behavior during sandboxed runs.