Skip to content
TrustedSkillsbeta
Back to all skills

Prompt Guard

Checked
orchestra-research·vlatest·ai-ml·MIT

Prompt Guard filters potentially harmful or irrelevant prompts, ensuring safer and more focused AI interactions for improved results.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add orchestra-research/ai-research-skills --skill prompt-guard -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

orchestra-research

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Makes no network calls.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned orchestra-research/ai-research-skills at 773a52944b.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
773a52944b
Manifest
07-safety-alignment/prompt-guard/SKILL.md
Scanned
1 file, 289 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

The prompt-guard skill provides a safety layer for AI agents by filtering inputs and outputs to prevent harmful or policy-violating interactions. It ensures that agent responses remain aligned with safety guidelines while processing user requests in real-time.

When to use it

  • Deploying autonomous agents that interact directly with end-users without human oversight.
  • Integrating AI tools into enterprise environments where data privacy and compliance are critical.
  • Preventing the generation of toxic, biased, or dangerous content during high-volume automated workflows.
  • Adding a secondary verification step before an agent executes sensitive actions based on user input.

Key capabilities

  • Real-time input validation to block malicious prompts before they reach the model.
  • Output filtering to intercept and sanitize potentially harmful responses generated by the agent.
  • Alignment enforcement to keep agent behavior within defined safety boundaries and ethical standards.

Example prompts

  • "Act as a customer support bot and respond to this angry user complaint without escalating the situation."
  • "Generate a list of creative ideas for a marketing campaign targeting a specific demographic."
  • "Analyze this code snippet and suggest optimizations while ensuring no security vulnerabilities are introduced."

Tips & gotchas

Ensure your safety rules are tuned to your specific use case, as overly strict filters may block legitimate user queries. Regularly review blocked logs to refine the guardrails and reduce false positives without compromising safety.