Prompt injection detection skill
What this skill does
Two-layer content safety for agent input and output. Use when (1) a user message attempts to override, ignore, or bypass previous instructions (prompt injection), (2) a user message references system prompts, hidden instructions, or internal configuration, (3) receiving messages from untrusted users in group chats or public channels, (4) generating responses that discuss violence, self-harm, sexual content, hate speech, or other sensitive topics, or (5) deploying agents in public-facing or multi-user environments where adversarial input is expected.
Prompt injection detection skill is part of the Developer Tools category — developer tools that help your agent write, review, debug, and ship code. You can install it on its own or alongside other developer tools skills from the OpenClaw catalog.
How to install Prompt injection detection skill
The easiest path is via the OpenClaw Easy desktop app — one click, no terminal required:
- Download OpenClaw Easy for macOS or Windows (free, one-click installer, ~30 seconds).
- Open the in-app Skills panel.
- Search for
detect-injectionand click Install. - The skill activates automatically when an incoming message matches its description.
Install from the command line
If you already run the OpenClaw CLI, add Prompt injection detection skill with a single command:
openclaw skills add detect-injection
This pulls detect-injection from ClawHub and installs it into ~/.openclaw/skills/detect-injection/. Restart the OpenClaw gateway afterwards so the new skill is discovered.
How to use Prompt injection detection skill
Once installed, Prompt injection detection skill activates on its own: when an incoming message on WhatsApp, Telegram, Slack, Discord, Feishu or Line matches the skill's description, your OpenClaw agent loads it and runs the workflow. You can also trigger it explicitly by describing the task in chat. No extra configuration is required after install.
Putting audio in front of an audience
Prompt injection detection skill works with audio. Getting from there to something postable is a separate job: ViralMint — an open-source video pipeline — pairs audio with footage or generated visuals, burns synced captions, and exports a finished short.
It runs as an MCP server, so an OpenClaw agent can drive it from the same chat you already use: ask for a short, and the render comes back finished. See how to connect a video pipeline to your agent.
Manual install (advanced)
If you prefer manual installation:
- Click the Download .zip button above to grab
detect-injection-1.0.0.zipdirectly from our S3 mirror. - Unzip into
~/.openclaw/skills/detect-injection/(create the directory if it does not exist). - Restart OpenClaw Easy (or the OpenClaw CLI gateway) so the new skill is discovered.
Frequently asked questions
How do I install Prompt injection detection skill?
Install Prompt injection detection skill in the OpenClaw Easy desktop app by opening the Skills panel, searching for detect-injection, and clicking Install. From a terminal you can run: openclaw skills add detect-injection. Either way the skill is placed in ~/.openclaw/skills/detect-injection/.
Is Prompt injection detection skill free?
Yes. Prompt injection detection skill is free and open-source, distributed under the Apache-2.0 license through ClawHub. No account or payment is required to download or run it.
What does Prompt injection detection skill do?
Two-layer content safety for agent input and output.
Related: more developer tools skills
If Prompt injection detection skill looks useful, you may also want to check out other developer tools skills in the OpenClaw catalog:
Browse the full OpenClaw skill catalog
This page covers just one skill. The OpenClaw skill hub has 10,000+ more — search, sort by downloads or stars, and install any of them in one click. There is also a curated awesome-openclaw-skills list grouped by use case.
Get OpenClaw Easy — Free
Install Prompt injection detection skill and 10,000+ other OpenClaw skills in one click. Free, open-source, runs locally on macOS & Windows.
Free, open-source · Apache-2.0 · Works with Claude, ChatGPT, Gemini, or local Ollama models