.claude/skills/ai-content-guardRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
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。
These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.
These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.
.claude/skills/ai-content-guardRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
.agents/skills/ai-content-guardRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
skills/ai-content-guardRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
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-guardclawhub inspect @a9320/ai-content-guard --version 1.3.2This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.
ignore previous instructionsignore previous instructionsignore previous instructionsignore all previous instructionsignore previous instructionsThis 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.
The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.
sha256:51f753fa11c827b0029eb8d844792a6a460a368449fdb1e4b58a1590945c4152_meta.jsonLICENSEpackage.jsonreferences/guidance.mdreferences/privacy.mdreferences/rules.mdreferences/security-notes.mdscripts/engine/__init__.pyscripts/engine/descriptions_en.pyscripts/engine/detectors.pyscripts/engine/ENGINE-ANCHOR.txtscripts/engine/report_lang.pyscripts/engine/rules.pyscripts/engine/sanitizer.pyscripts/engine/sarif.pyscripts/engine/scan.pyscripts/engine/zh_rules.pyscripts/entry.pyskill-card.mdSKILL.mdv1.3.2: 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