openafw

Propose changes to the openafw (afw) OGR gateway security policy — the detectors that guard an agent's traffic on the wire. Use this when the operator asks to tighten or loosen afw's guardrails: change how prompt injection or secret leakage is handled, or add/remove a command rule (e.g. "block rm -rf", "hold curl|bash for approval", "stop redacting secrets"). You DRAFT and PROPOSE; a human must APPROVE before anything takes effect.

MoltGuard — Protect you and your human from prompt injection, data exfiltration, and malicious commands. Source: https://github.com/openguardrails/openguardrails/tree/main/moltguard