← Back to Skills Marketplace
140
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install promptguard
Description
Detect prompt injection attacks in text. Returns risk score and detected patterns.
Usage Guidance
This skill appears to be a straightforward, local prompt-injection scanner. Before installing: (1) confirm how your platform implements the install 'uv' step (ensure it installs from trusted PyPI sources); (2) don't expose the server publicly without authentication because the provided service accepts arbitrary text and has no auth built in; (3) keep dependencies up to date and run in an isolated environment if you are concerned about supply-chain risk; (4) test with representative inputs to validate detection coverage and false positives/negatives for your use case.
Capability Analysis
Type: OpenClaw Skill
Name: promptguard
Version: 0.1.1
The 'promptguard' skill is a legitimate security utility designed to detect prompt injection patterns using regex-based heuristics. The codebase (FastAPI, Pydantic, and regex detectors in promptguard/detectors.py) is transparent, lacks any suspicious network or file system activity, and contains no evidence of malicious intent or prompt injection attacks against the AI agent.
Capability Assessment
Purpose & Capability
Name/description, required binaries (python), declared Python packages, and the included source code all match a simple local prompt-injection detector. Nothing in the files indicates unrelated capabilities (cloud access, system configuration, or secrets handling).
Instruction Scope
SKILL.md instructs to install FastAPI/uvicorn/pydantic, run uvicorn to start the server, and POST text to /v1/scan. The code implements exactly that endpoint and only inspects the provided text; it does not read files, environment variables, or external endpoints.
Install Mechanism
The declared packages are standard PyPI packages (fastapi, uvicorn, pydantic), which is appropriate. The install 'kind' is listed as 'uv' in metadata (unusual/ambiguous), but the SKILL.md shows pip instructions and the code is pure Python — this looks low risk but you may want to confirm how your platform's installer resolves 'uv'.
Credentials
No environment variables, credentials, or config paths are requested. The skill does not attempt to access unrelated secrets or system config.
Persistence & Privilege
always is false and the skill does not try to modify other skills or system-wide settings. It runs as a local HTTP service and requires explicit startup; it does not persist elevated privileges.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install promptguard - After installation, invoke the skill by name or use
/promptguard - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.1
- Added metadata for installation requirements and dependencies.
- Documented required Python packages and installation steps.
- Updated usage instructions for running the API server and making requests.
- Improved clarity and structure of setup and usage guidance.
v0.1.0
Initial release of promptguard — detect prompt injection attacks in text.
- Scans input text for common prompt injection patterns.
- Returns a risk score (0.0-1.0) and a list of detected attack patterns.
- Supports detection of instruction overrides, HTML comment injection, zero-width characters, delimiter attacks, role switching, and system prompt extraction.
- Available as a hosted API and as a standalone FastAPI app.
- Simple JSON input/output structure for easy integration.
Metadata
Frequently Asked Questions
What is Promptguard?
Detect prompt injection attacks in text. Returns risk score and detected patterns. It is an AI Agent Skill for Claude Code / OpenClaw, with 140 downloads so far.
How do I install Promptguard?
Run "/install promptguard" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Promptguard free?
Yes, Promptguard is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Promptguard support?
Promptguard is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Promptguard?
It is built and maintained by mirni (@mirni); the current version is v0.1.1.
More Skills