Real Skill packageSource verifiedClawHub registry

ai-content-guard

AI 内容安检:检测文本、文件、网页和邮件中的提示注入、隐形字符、编码载荷和 AI 配置文件后门;纯本地确定性引擎,零网络零依赖,输出四值判决、脱敏证据与处置建议。读取来自外部或不可信来源的脚本、配置、文档、仓库代码前也先扫。

Identity and source

Publisher attributionYANG WEI KEregistry owner unverified by skillvetai
Functional categoryWriting, Content & Translationautomatically inferred · 57% rule confidence
Package forminstruction with code20 recorded files
Canonical sourceClawHub registryclawhub:a9320:ai-content-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 · 11/9/2026.claude/skills/ai-content-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 · 11/9/2026.agents/skills/ai-content-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 · 11/9/2026skills/ai-content-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 @a9320/ai-content-guard
clawhub inspect @a9320/ai-content-guard --version 1.3.2

Security evidence

SkillVetAI static result: medium 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
20 / 20 inspected as text
Checked
11/9/2026, 6:36:03 AM
Scanner
0.1.3
Policy
1.0.3
5 automated findings
mediumPrompt-override language requires reviewscripts/engine/descriptions_en.py:27 · confidence 62%ignore previous instructions
mediumPrompt-override language requires reviewscripts/engine/detectors.py:351 · confidence 62%ignore previous instructions
mediumPrompt-override language requires reviewscripts/engine/rules.py:117 · confidence 62%ignore previous instructions
mediumPrompt-override language requires reviewscripts/engine/zh_rules.py:213 · confidence 62%ignore all previous instructions
mediumPrompt-override language requires reviewreferences/rules.md:30 · confidence 62%ignore previous instructions
4 inferred permission indicators
  • network access — automatically inferred
  • filesystem read — automatically inferred
  • filesystem write — automatically inferred
  • credential access — automatically inferred
6 dependency and API indicators
  • api: clawhub.ai
  • api: docs.oasis-open.org
  • api: embracethered.com
  • api: github.com
  • api: nvd.nist.gov
  • api: trojansource.codes
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
11/8/2026, 9:07:58 AM
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 hashsha256:51f753fa11c827b0029eb8d844792a6a460a368449fdb1e4b58a1590945c4152
Show up to 20 recorded paths
  • _meta.json
  • LICENSE
  • package.json
  • references/guidance.md
  • references/privacy.md
  • references/rules.md
  • references/security-notes.md
  • scripts/engine/__init__.py
  • scripts/engine/descriptions_en.py
  • scripts/engine/detectors.py
  • scripts/engine/ENGINE-ANCHOR.txt
  • scripts/engine/report_lang.py
  • scripts/engine/rules.py
  • scripts/engine/sanitizer.py
  • scripts/engine/sarif.py
  • scripts/engine/scan.py
  • scripts/engine/zh_rules.py
  • scripts/entry.py
  • skill-card.md
  • SKILL.md

Source changelog

v1.3.2: all 7 improvement items from the independent 38-finding triage addressed (sensitive-file glob, minimal-permission manifest, narrowed trigger scope, full-stage fault tolerance, symlink check before resolve, i18n verdict template); detection rules and verdict logic unchanged