LaunchKit · 2026
Back to Skills

agentshield-audit

Initiate and manage AgentShield security audits for AI agents.

0
660 downloads
by @bartelmost

Setup & Installation

openclaw skills install @bartelmost/agentshield-audit

Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:

npx clawhub install agentshield-audit

Version History

v1.0.22Mar 11, 2026 - Version note by skill developer:

v1.0.22 - Security & Documentation Update FIXED: • Hardcoded Heroku URL → agentshield.live/api (domain-aligned) ADDED: • Data Transmission Transparency section (explicit JSON examples) • Consent Flow documentation (BEFORE file access) • PRIVACY.md - Complete data handling guide ADDRESSES: • OpenClaw scanner concerns from v1.0.21 • Expected: Benign/Low Risk rating No breaking changes. Same 77 tests + Trust Handshake Protocol.

What This Skill Does

AgentShield adds a cryptographic trust layer to AI agent communication. It runs 77 security tests locally against an agent and issues Ed25519 certificates through a public Trust Registry. Two certified agents can then perform a Trust Handshake Protocol to mutually verify identities and establish an encrypted session key.

Without a dedicated trust layer, agent-to-agent communication has no standard way to verify identity or security posture, leaving interactions as unverifiable as HTTP without TLS.

When to use it

  • Auditing a new agent before adding it to a multi-agent pipeline
  • Verifying a third-party agent's certificate before sharing sensitive data with it
  • Getting your agent certified for listing in an agent marketplace
  • Establishing an encrypted session key before delegating tasks to a sub-agent
  • Checking another agent's trust tier and handshake history in the public registry

Example Workflow

Here's how your AI assistant might use this skill in practice.

INPUT

User asks: audit my agent and run a trust handshake with agent_yyyyy

AGENT
  1. 1Runs 77 security tests locally against the agent, covering prompt injection, encoding exploits, social engineering vectors, and 25 static checks
  2. 2Submits public key and test score summary to AgentShield API to obtain an Ed25519 certificate
  3. 3Looks up agent_yyyyy in the Public Trust Registry to check its tier and reputation score
  4. 4Initiates Trust Handshake Protocol with agent_yyyyy, both agents sign cryptographic challenges server-side
  5. 5Receives a shared session key upon successful mutual verification
OUTPUT

Security score (0-100), a 90-day certificate with public verification URL, and a shared AES-256 compatible session key for encrypted communication with agent_yyyyy