Skip to content
TrustedSkillsbeta
Back to all skills

Agent Guardrails

Listed
jzocb·vlatest·agents·MIT

jzocb's agent-guardrails enforces safety protocols and ethical boundaries within your AI agent’s interactions.

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 jzocb/agent-guardrails --skill agent-guardrails -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

jzocb

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 failed 2 of 6 checks. A failure is not proof of bad intent; it means something in the code needs a human to look at it before you run it.

  • No undeclared network calls: failed

    Contacts 1 host that is neither well-known infrastructure nor declared in the skill's frontmatter: clawdhub.com.

    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.

    Hosts contacted

    clawdhub.comundeclared

    What it found

    • PUBLISH_NOW.sh:34contacts clawdhub.com
      echo "View at: https://clawdhub.com/skills/agent-guardrails"

  • No credential access: failed

    Touches credential material in 2 places.

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

    What it found

    • scripts/check-secrets.sh:138SSH private keys or config
      for pattern in '.env' '.env.*' '*.key' '*.pem' '*.p12' '*.pfx' 'id_rsa' 'id_ed25519' 'credentials.json'; do
    • scripts/check-secrets.sh:155SSH private keys or config
      for pattern in '.env' '.env.*' '*.pem' '*.key' '*.p12' '*.pfx' 'credentials.json' 'service-account*.json' '*.keystore' 'id_rsa' 'id_ed25519'; do

  • 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 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 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 jzocb/agent-guardrails at bebef1b24d.

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

Commit
bebef1b24d
Manifest
SKILL.md
Scanned
23 files, 3,024 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

What it does

This skill provides a framework for defining and enforcing constraints on AI agent behavior. It allows developers to specify rules that agents must adhere to, preventing undesirable actions or outputs. The skill helps ensure agents operate safely and ethically within defined boundaries.

When to use it

  • Content Moderation: When building an agent that generates text content (e.g., a chatbot), to prevent the generation of harmful or inappropriate responses.
  • Data Privacy: To restrict an agent's access to sensitive data, ensuring compliance with privacy regulations.
  • Task Boundaries: When defining specific tasks for an agent, to prevent it from straying outside those boundaries and performing unintended actions.
  • Safety-Critical Applications: In scenarios where agent behavior has real-world consequences (e.g., automated control systems), to guarantee safe operation.

Key capabilities

  • Constraint definition
  • Behavior enforcement
  • Rule specification
  • Boundary setting

Example prompts

  • "Define a rule that prevents the agent from disclosing personal information."
  • "Restrict the agent's access to financial data."
  • "Ensure the agent only responds to questions about weather forecasts."

Tips & gotchas

The effectiveness of this skill depends on clearly defining and testing your guardrail rules. Insufficient or poorly defined rules may not prevent all undesirable behavior.