Real Skill packageSource verifiedClawHub registry

agent-command-guard-hardening

Harden an agent's command interception layer safely: snapshot the baseline, test a matrix of should-block, negative-control, and known-bypass cases, verify classification rather than executing destructive commands, and document the bypass surface. Use when adding or changing guards around rm, mv, chmod, sudo, launchctl, dd, or any command wrapper. Tool-agnostic; includes a matrix runner and a bypass scanner.

Identity and source

Publisher attributioncengcengcai-creatorregistry owner unverified by skillvetai
Functional categoryAgent Engineering, Security & Governanceautomatically inferred · 68% rule confidence
Package forminstruction with code10 recorded files
Canonical sourceClawHub registryclawhub:cengcengcai-creator:agent-command-guard-hardening
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 · 11/8/2026.claude/skills/agent-command-guard-hardening

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 · 11/8/2026.agents/skills/agent-command-guard-hardening

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 · 11/8/2026skills/agent-command-guard-hardening

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 @cengcengcai-creator/agent-command-guard-hardening
clawhub inspect @cengcengcai-creator/agent-command-guard-hardening --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
10 / 10 inspected as text
Checked
11/8/2026, 5:59:45 AM
Scanner
0.1.3
Policy
1.0.3
4 automated findings
highRemote content is piped directly to a shellexamples/scripts-sample.sh:7 · confidence 98%curl -sS https://example.com/install.sh | bash
mediumWorld-writable permissions are requestedSKILL.md:52 · confidence 95%chmod -R 777
mediumWorld-writable permissions are requestedexamples/scripts-sample.sh:4 · confidence 95%chmod -R 777
mediumRemote installer is downloaded without an integrity checkexamples/scripts-sample.sh:7 · confidence 70%curl -sS https://example.com/install.sh
1 High/Critical review queue entry
STATIC_DOWNLOAD_PIPE_TO_SHELLpending
Open human review queue →
4 inferred permission indicators
  • shell execution — automatically inferred
  • network access — automatically inferred
  • filesystem read — automatically inferred
  • filesystem write — automatically inferred
1 dependency and API indicators
  • api: clawhub.ai
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
11/7/2026, 3:24:20 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:f583f5a8a1e213a08460a9be1a772fca8f61b90282ab1bb763c355414c1dc30e
Show up to 10 recorded paths
  • examples/classifier-demo.sh
  • examples/matrix.json
  • examples/scripts-sample.sh
  • LICENSE
  • README.md
  • references/bypass-surfaces.md
  • scripts/bypass_scan.py
  • scripts/matrix_run.py
  • skill-card.md
  • SKILL.md

Source changelog

- Added a reproducible workflow for hardening command guards, from baseline snapshots through rollback. - Required a before-and-after test matrix covering blocked commands, negative controls, and known bypasses—using classification, never destructive execution. - Added guidance for shared wrapper design, syntax checks, decision logging, and documenting residual bypass risks. - Clarified that command wrappers are not security boundaries and that detection should be separate from blocking.