Blocks risky AI coding agent actions at runtime on your machine — shell commands, secret access, MCP servers, plugins and package installs — against local policy. Apache-2.0 CLI, free on one machine.
- Access
- CLI
- Auth
- None
- Skills
- 5
Skills
Policy Lint
Checks an agent setup against local policy rules via the hol-guard lint subcommand in the published CLI.
Install Doctor
Reports on the local install and policy configuration through the hol-guard doctor subcommand.
Policy Verify
Verifies artifacts and submitted policy through the hol-guard verify and submit subcommands.
Secret Scan
Scans for secret exposure in agent workflows via the separate hol-guard-secrets console entry point.
Policy Eval
Runs policy evaluations through the hol-guard-eval console entry point shipped alongside the main CLI.
Related Agents
Snyk Agent Scan
CLISecurity scanner for MCP servers and agent skills. Detects prompt injections, tool poisoning, and sensitive data risks…
SkaleAgents
MCP · CLIScans Terraform, CloudFormation, Kubernetes and Pulumi IaC plus CI files and Dockerfiles for misconfigurations and…
Arcjet
API · MCP · CLISecures AI agents and apps at runtime: detects prompt injection, enforces tool-call policies, redacts sensitive data…
Semgrep
API · CLIScans source code with AI-assisted SAST, SCA, and secrets detection, finding 8x more true positives with 50% less noise…