Community warnings
Real attacks, caught and broken down.
Real security incidents from AI coding sessions — what happened, why it was dangerous, and how Guard stopped it. All sensitive data removed before publishing.
Redacted by default
No raw prompts
No private paths
Hidden until moderated
Redacted warnings
Real protection moments, scrubbed for safety before becoming public learning pages.
codex
Codex was stopped before reading an env file
A redacted example of a local secret read attempt.
Open guideclaude-code
Claude Code was stopped before calling an untrusted MCP tool
A redacted example of an MCP tool with a misleading description.
Open guidecursor
Cursor was stopped before following a hidden instruction
A redacted example of a prompt injection via a file comment.
Open guideopencode
OpenCode was stopped before running a malicious postinstall script
A redacted example of a supply-chain attack via npm install.
Open guide