
hol-guard
Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at…

Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at…

Security control plane for LLM agents: allowlists, owner kill switch, PIN sessions, rate limits, prompt-injection detection, and output scrubbing to…

Credential and sensitive-data exposure triage for file shares

Embed multiple secret messages in LLM chat token choices using arithmetic/Discop steganographic coders, with bit-exact decoding and steganalysis…

Strip credential-like content from free-form strings before they reach logs or telemetry. Part of the phpboyscout Go toolkit. ·…

PISIGuard runs entirely in your browser. It spots names, email addresses, phone numbers, credit card numbers, passwords, API keys, and more, replaces…

Self-hosted runtime control plane for AI agents. Observe or HITL approve or Block rogue tool calls before it executes: secret leaks, prompt…

Keep it secret, keep it safe