← Back to Skills Marketplace
Gws Modelarmor Sanitize Prompt
by
googleworkspace-bot
· GitHub ↗
· v1.0.12
· MIT-0
417
Downloads
0
Stars
12
Active Installs
13
Versions
Install in OpenClaw
/install gws-modelarmor-sanitize-prompt
Description
Google Model Armor: Sanitize a user prompt through a Model Armor template.
README (SKILL.md)
modelarmor +sanitize-prompt
PREREQUISITE: Read
../gws-shared/SKILL.mdfor auth, global flags, and security rules. If missing, rungws generate-skillsto create it.
Sanitize a user prompt through a Model Armor template
Usage
gws modelarmor +sanitize-prompt --template \x3CNAME>
Flags
| Flag | Required | Default | Description |
|---|---|---|---|
--template |
✓ | — | Full template resource name (projects/PROJECT/locations/LOCATION/templates/TEMPLATE) |
--text |
— | — | Text content to sanitize |
--json |
— | — | Full JSON request body (overrides --text) |
Examples
gws modelarmor +sanitize-prompt --template projects/P/locations/L/templates/T --text 'user input'
echo 'prompt' | gws modelarmor +sanitize-prompt --template ...
Tips
- If neither --text nor --json is given, reads from stdin.
- For outbound safety, use +sanitize-response instead.
See Also
- gws-shared — Global flags and auth
- gws-modelarmor — All filter user-generated content for safety commands
Usage Guidance
This skill is a simple wrapper that calls the 'gws' CLI to sanitize prompts. Before installing or enabling it: (1) verify the 'gws' binary is the legitimate tool you expect and is installed from a trusted source; (2) open and read ../gws-shared/SKILL.md (or the output of 'gws generate-skills') to see what authentication or global flags it requires — that file may request credentials or configure behavior not declared here; (3) be aware that sanitized text will be sent to whatever backend 'gws' communicates with (likely a Google service), so avoid passing sensitive secrets through the prompt unless you trust that flow. If you cannot access or audit gws-shared, treat this skill with caution.
Capability Analysis
Type: OpenClaw Skill
Name: gws-modelarmor-sanitize-prompt
Version: 1.0.12
The skill bundle is a standard documentation wrapper for the 'gws' CLI tool, specifically for interacting with Google Cloud's Model Armor service to sanitize prompts. No malicious code, data exfiltration, or prompt injection attempts were found in SKILL.md or _meta.json.
Capability Assessment
Purpose & Capability
The skill's name/description match what the SKILL.md instructs: run the 'gws modelarmor +sanitize-prompt' command. Requiring the 'gws' binary is coherent with the stated purpose and no unrelated binaries or installs are requested.
Instruction Scope
The runtime instructions are narrow and only describe invoking the gws CLI with --template/--text/--json and reading stdin. However the SKILL.md explicitly points to ../gws-shared/SKILL.md for auth, global flags, and security rules and suggests running 'gws generate-skills' if missing — you should review that shared file because it governs authentication and any additional behavior not declared here.
Install Mechanism
No install spec and no code files (instruction-only). This minimizes risk from arbitrary downloads or writes to disk.
Credentials
The skill itself declares no env vars or credentials, but it defers auth and global flags to ../gws-shared/SKILL.md. That external file may require credentials or configuration not visible here; the lack of declared credentials in this skill is therefore incomplete and should be verified by inspecting gws-shared.
Persistence & Privilege
always is false and the skill does not request system persistence or elevated privileges. Nothing in this SKILL.md indicates it will modify other skills or system-wide agent settings.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install gws-modelarmor-sanitize-prompt - After installation, invoke the skill by name or use
/gws-modelarmor-sanitize-prompt - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.12
- Updated skill metadata version from 0.22.4 to 0.22.5 in SKILL.md.
v1.0.11
- Updated metadata version to 0.22.4 in SKILL.md
- No other changes made
v1.0.10
- Bumped metadata version from 0.22.2 to 0.22.3 in SKILL.md.
- No other content changes.
v1.0.9
- Updated metadata version from 0.22.1 to 0.22.2 in SKILL.md.
v1.0.8
- Updated version metadata from 0.22.0 to 0.22.1 in SKILL.md
v1.0.7
- Updated version in metadata from 0.21.2 to 0.22.0 in SKILL.md.
- No other changes made to documentation or functionality.
v1.0.6
- Bumped internal version in metadata from 0.21.1 to 0.21.2 in SKILL.md.
- No other content or functionality changes.
v1.0.5
- Updated skill metadata version from 0.20.1 to 0.21.1 in SKILL.md.
- No other content or functional changes.
v1.0.4
- Version bumped from 0.20.0 to 0.20.1 in metadata.
- No other changes made to documentation or functionality.
v1.0.3
- Updated version number in SKILL.md from 0.19.0 to 0.20.0.
v1.0.2
- Updated SKILL.md metadata: moved version under metadata and set to 0.19.0.
- Removed explicit top-level version field from SKILL.md.
- No changes to usage, flags, examples, or documentation content.
v1.0.1
- Minor formatting update to the SKILL.md metadata: switched "bins: [gws]" to a YAML list format.
- No functional or user-facing changes.
v1.0.0
Initial release of the gws-modelarmor-sanitize-prompt skill.
- Introduces a command to sanitize user prompts using a Model Armor template.
- Supports input via --text, --json, or stdin.
- Requires specifying a full template resource name.
- Includes CLI help, usage examples, and tips for outbound safety.
- Linked documentation for shared flags, authentication, and related Model Armor skills.
Metadata
Frequently Asked Questions
What is Gws Modelarmor Sanitize Prompt?
Google Model Armor: Sanitize a user prompt through a Model Armor template. It is an AI Agent Skill for Claude Code / OpenClaw, with 417 downloads so far.
How do I install Gws Modelarmor Sanitize Prompt?
Run "/install gws-modelarmor-sanitize-prompt" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Gws Modelarmor Sanitize Prompt free?
Yes, Gws Modelarmor Sanitize Prompt is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Gws Modelarmor Sanitize Prompt support?
Gws Modelarmor Sanitize Prompt is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Gws Modelarmor Sanitize Prompt?
It is built and maintained by googleworkspace-bot (@googleworkspace-bot); the current version is v1.0.12.
More Skills