AI antivirus for agentic code

Stop risky AI actions before they become incidents.

HOL Guard watches coding agents, MCP servers, skills, plugins, and local commands. Start with protection, then use these guides to understand the threats Guard is built to catch.

First minute path

1Agent asks to actA harness wants to read a file, run shell, call MCP, or install a skill.
2Guard pauses riskLocal review opens before damage, not after logs are already written.
3Your choice becomes memoryApproved, blocked, and repeated patterns turn into team policy.
4Cloud explains the patternWarnings, labs, and guides teach what happened without leaking private work.

Choose what you need from Guard right now.

Security content should move you toward action. Pick the path that matches your moment.

Public proof, private work protected.

Redacted warnings show why Guard intervened without publishing raw prompts, tokens, paths, or private code.

Read redacted warning

Practice safely before your next incident.

Labs are static simulations. They teach what Guard would do without executing dangerous commands.

Start Prompt injection replay

Security advisories

Real attacks against AI agents and developer tools, with detection steps and fixes.

mcp-tool-poisoning

MCP tool description poisoning

Malicious MCP tool descriptions embed hidden instructions that redirect AI agents into calling the wrong tool, exfiltrating secrets, or executing unintended commands — even when the tool itself appears harmless.

Open guide

prompt-injection

Prompt injection via issue comments and pull requests

Attackers embed hidden instructions in GitHub issues, PR comments, and commit messages. When an AI agent reads these to help triage or review, it follows the embedded instructions — potentially approving malicious code or leaking repository secrets.

Open guide

supply-chain

npm postinstall script abuse in AI coding environments

Malicious npm packages use postinstall scripts to execute arbitrary code during installation. In AI coding environments, these scripts can modify agent configuration, install backdoor MCP servers, or exfiltrate project secrets — all before the developer reviews the package.

Open guide

mcp-tool-poisoning

Shadow MCP server discovery and persistent access

MCP servers added to a project during development can persist in configuration files and maintain access to the agent’s context window long after they are forgotten. These "shadow" servers continue receiving tool calls and may be modified by attackers who compromise the original server.

Open guide

prompt-injection

Agent-readable config file poisoning

AI agents read configuration files like CLAUDE.md, .cursorrules, and AGENTS.md as trusted context. An attacker who can modify these files — via a compromised dependency, a malicious collaborator, or a typo in a path — gains the ability to inject persistent instructions the agent follows on every session.

Open guide

secret-exfiltration

Environment file exfiltration via webhook

AI agents can be tricked into reading .env files and sending their contents to external endpoints through tool calls, webhook integrations, or HTTP requests that appear legitimate.

Open guide

data-overexposure

Context window scraping via long file reads

AI agents that read large files can leak proprietary code, internal documentation, and customer data into their context window — which may then be sent to external LLM APIs or logged in cloud telemetry.

Open guide

unsafe-command

Destructive command execution via injected instruction

Prompt injection can cause AI agents to run destructive shell commands like rm -rf, git push --force, or database drops — by embedding instructions in files, issues, or tool descriptions.

Open guide

data-overexposure

Cross-workspace credential leak via monorepo traversal

AI agents in monorepo environments can read credentials, configs, and secrets from adjacent workspaces — leaking data across team boundaries.

Open guide

prompt-injection

Clipboard and terminal buffer injection

Attackers can plant hostile instructions in clipboard contents or terminal scrollback buffers. When an AI agent reads terminal output or the user pastes clipboard content, the hidden instructions execute as if they came from the user.

Open guide

secret-exfiltration

Gitignore bypass via agent file reads

AI agents can read files that are gitignored — secrets, private keys, and internal configs — because gitignore only prevents git tracking, not file system access. These files often contain the most sensitive data in a repository.

Open guide

secret-exfiltration

MCP authentication token theft via headers

MCP servers that accept authentication tokens in headers can leak those tokens if the server logs requests, shares telemetry, or is compromised. Tokens passed to MCP servers persist in server-side logs and may be accessible to attackers.

Open guide

prompt-injection

Malicious skill with hidden prompt injection

AI agent skills (Claude Code skills, Cursor rules, Copilot extensions) can contain hidden prompt injections in their instructions. When the skill is loaded, the hidden prompt executes on every session that uses the skill.

Open guide

mcp-tool-poisoning

Tool permission creep in AI agents

AI agents accumulate tool permissions over time as developers approve new tools "just this once." These permissions persist across sessions, creating an ever-widening attack surface where tools that were approved once can be used by prompt injection in future sessions.

Open guide

prompt-injection

Indirect prompt injection via web content

When AI agents fetch web pages — documentation, Stack Overflow answers, package READMEs — the fetched content can contain hidden instructions that the agent follows, potentially exfiltrating data or executing unintended actions.

Open guide

prompt-injection

Agent identity spoofing via system prompt mimicry

Attackers can craft content that mimics system prompts or tool outputs, tricking the agent into believing it received instructions from the harness, the user, or a trusted tool — when the instructions actually came from untrusted data.

Open guide

supply-chain

Dockerfile injection via AI agent writes

When AI agents write or modify Dockerfiles, prompt injection can cause them to add malicious instructions — pulling attacker-controlled base images, exfiltrating build secrets, or installing backdoors that persist across all container builds.

Open guide

supply-chain

CI/CD pipeline poisoning via agent-written config

AI agents that write CI/CD configuration files (GitHub Actions, GitLab CI, CircleCI) can introduce backdoors — injecting steps that exfiltrate secrets, modify artifacts, or deploy malicious code — that execute on every build.

Open guide

prompt-injection

Model confusion via conflicting instructions

When an AI agent receives multiple conflicting instructions — from the user, the system prompt, tool descriptions, and file contents — it may follow the wrong one. Attackers exploit this by planting instructions that conflict with the user's actual intent.

Open guide

data-overexposure

Excessive file reading during project exploration

When AI agents explore a project to understand its structure, they often read dozens or hundreds of files — far more than needed for the task. This excessive reading can expose secrets, proprietary code, and customer data that enter the context window and model API.

Open guide

supply-chain

Stale dependency exploitation in AI environments

AI agents often work with projects that have outdated dependencies. When an agent suggests or installs packages based on a stale package.json, it can introduce known-vulnerable versions — and in AI environments, the vulnerability is amplified because the agent can execute commands.

Open guide

data-overexposure

Token cost amplification via context flooding

Attackers can craft content that causes AI agents to consume excessive tokens — by inserting large files, repetitive instructions, or recursive prompts that bloat the context window. This inflates API costs and can cause rate-limit denial of service.

Open guide