Threat explainer
Model data egress
How AI agents send your code, prompts, and data to external LLM APIs and model endpoints.
- 01
AI tools send your code to cloud APIs. You should know where it goes.
- 02
Model egress risk arises when an agent sends proprietary code, internal context, or user data to a remote LLM API — potentially leaking IP to model providers or third-party inference endpoints.
- 03
HOL Guard turns these moments into private receipts first, then public lessons only after redaction and moderation.
Harness setup guides
Protect the coding tools your team already uses without forcing everyone to become a security expert.
Claude Code
Agentic coding harness with MCP and file access.
Open guideharnessGitHub Copilot CLI
IDE and CLI assistant across code and terminal flows.
Open guideharnessCursor
AI-first IDE with repo and terminal context.
Open guideharnessGemini CLI
Command-line agent workflow for local projects.
Open guideRedacted warnings
Real protection moments, scrubbed for safety before becoming public learning pages.
Codex was stopped before reading an env file
A redacted example of a local secret read attempt.
Why it was risky
Env files often hold API keys or service credentials.
What Guard did
HOL Guard paused the read before file contents left the machine.
Claude Code was stopped before calling an untrusted MCP tool
A redacted example of an MCP tool with a misleading description.
Why it was risky
The tool description asked the agent to read credentials and pass them as arguments.
What Guard did
HOL Guard paused the tool call and flagged the description for review.
Cursor was stopped before following a hidden instruction
A redacted example of a prompt injection via a file comment.
Why it was risky
The instruction was embedded in an HTML comment invisible to the developer.
What Guard did
HOL Guard paused the command and showed the source of the instruction.
OpenCode was stopped before running a malicious postinstall script
A redacted example of a supply-chain attack via npm install.
Why it was risky
Postinstall scripts run with full permissions before anyone reviews the code.
What Guard did
HOL Guard paused the install and showed the script contents.
Safe labs
Practice attack patterns with static simulations. Nothing dangerous executes.