← 返回 Skills 市场
Gws Modelarmor
作者
googleworkspace-bot
· GitHub ↗
· v1.0.12
· MIT-0
455
总下载
0
收藏
13
当前安装
13
版本数
在 OpenClaw 中安装
/install gws-modelarmor
功能描述
Google Model Armor: Filter user-generated content for safety.
使用说明 (SKILL.md)
modelarmor (v1)
PREREQUISITE: Read
../gws-shared/SKILL.mdfor auth, global flags, and security rules. If missing, rungws generate-skillsto create it.
gws modelarmor \x3Cresource> \x3Cmethod> [flags]
Helper Commands
| Command | Description |
|---|---|
+sanitize-prompt |
Sanitize a user prompt through a Model Armor template |
+sanitize-response |
Sanitize a model response through a Model Armor template |
+create-template |
Create a new Model Armor template |
Discovering Commands
Before calling any API method, inspect it:
# Browse resources and methods
gws modelarmor --help
# Inspect a method's required params, types, and defaults
gws schema modelarmor.\x3Cresource>.\x3Cmethod>
Use gws schema output to build your --params and --json flags.
安全使用建议
This skill is an instruction-only wrapper around a 'gws' CLI. Before installing, verify the source and trustworthiness of the 'gws' binary (who provides it, official repo, checksums). Open and inspect the referenced ../gws-shared/SKILL.md to see how authentication and global flags are handled — it may contain credentials or instructions that create/configure auth artifacts. Also inspect the helper SKILL.md files mentioned (sanitize-prompt, sanitize-response, create-template) to ensure they don't introduce unexpected behavior. If you cannot locate the origin/homepage of the 'gws' tool or the shared SKILL.md, treat this skill as untrusted because it can cause the agent to read or create configuration files and call an external CLI with network access.
功能分析
Type: OpenClaw Skill
Name: gws-modelarmor
Version: 1.0.12
The gws-modelarmor skill is a standard interface for interacting with Google Model Armor via the 'gws' CLI. The SKILL.md file provides legitimate instructions for discovering API methods and using helper commands for content sanitization, with no evidence of malicious intent, data exfiltration, or prompt injection.
能力评估
Purpose & Capability
The skill's name/description (Model Armor content filtering) align with its instructions to call 'gws modelarmor' and inspect schema; requiring a 'gws' binary is reasonable for a CLI wrapper.
Instruction Scope
SKILL.md explicitly instructs the agent to read '../gws-shared/SKILL.md' for auth/global flags and to run 'gws generate-skills' if missing. That directs agent access to a file outside the skill's own directory and to create files, which expands scope and requires trust in what that shared file contains.
Install Mechanism
No install spec or code is present (instruction-only), so nothing is written by the skill itself. The runtime depends solely on an existing 'gws' binary.
Credentials
The skill declares no required env vars or credentials, yet points to a shared SKILL.md for auth and global flags. This non-disclosure of how authentication is handled (env, config files, or other) reduces transparency and is disproportionate.
Persistence & Privilege
always:false and no code means no forced persistence, but the instructions encourage creating/reading a shared config file via 'gws generate-skills', which could modify agent files or create persistent auth artifacts — acceptable if trusted, but worth reviewing.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install gws-modelarmor - 安装完成后，直接呼叫该 Skill 的名称或使用
/gws-modelarmor触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.12
- Updated skill version from 0.22.4 to 0.22.5 in metadata.
- No functional or documentation changes beyond the version increment.
v1.0.11
- Updated version number in SKILL.md from 0.22.3 to 0.22.4.
v1.0.10
- Updated version to 0.22.3 in metadata.
- No other changes to commands or documentation content.
v1.0.9
- Updated internal version metadata to 0.22.2.
- No other changes; documentation and functionality remain the same.
v1.0.8
- Bumped version from 0.22.0 to 0.22.1 in metadata.
- Documentation updated; no functional or command changes.
v1.0.7
- Bumped skill version to 0.22.0 (from 0.21.2) in metadata.
- No command or usage changes; documentation and functionality remain the same.
v1.0.6
- Updated version metadata from 0.21.1 to 0.21.2 in SKILL.md.
v1.0.5
- Updated metadata version from 0.20.1 to 0.21.1 in SKILL.md.
v1.0.4
- Updated version number in SKILL.md from 0.20.0 to 0.20.1.
- No other changes to functionality or documentation.
v1.0.3
- Bumped version to 0.20.0 in metadata.
- No functional or documentation changes outside of the version update in SKILL.md.
v1.0.2
- Updated skill metadata format and moved version info under the metadata section.
- Removed top-level version field.
- No functional or command changes; documentation and metadata only.
v1.0.1
- Updated SKILL.md formatting for consistency (no functional changes).
- Minor YAML formatting adjustment: changed to block list for "bins".
v1.0.0
Initial release of gws-modelarmor: filter user-generated content for safety.
- Provides CLI integration for Google Model Armor content filtering.
- Includes helper commands to sanitize user prompts and model responses.
- Supports creation of custom Model Armor templates.
- Offers documentation for browsing resources and inspecting method schemas.
- Requires prerequisites described in gws-shared for authentication and security.
元数据
常见问题
Gws Modelarmor 是什么？
Google Model Armor: Filter user-generated content for safety. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 455 次。
如何安装 Gws Modelarmor？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install gws-modelarmor」即可一键安装，无需额外配置。
Gws Modelarmor 是免费的吗？
是的，Gws Modelarmor 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Gws Modelarmor 支持哪些平台？
Gws Modelarmor 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Gws Modelarmor？
由 googleworkspace-bot（@googleworkspace-bot）开发并维护，当前版本 v1.0.12。
推荐 Skills