[!] TOPIC ARCHIVE // #AI-SECURITY
#Ai-Security
All 3 guides, operator dossiers, and signals tagged with #Ai-Security.
RADAR SIGNALRADAR SIGNALENTRY
hidden marks, owned memory, parser risk
Claude Code prompt marks, host-owned agent memory, and a protobuf parser bug pushed today’s control story into the small layers.
loops, gateways, and signed traces
agent work moved below the model today: outer loops, Rust gateways, framework audit logs, and signed red-team traces became the surfaces operators have to maintain.
prompt injection is killing self-hosted LLM deployments (and nobody's talking about it)
Enterprises moved to self-hosted AI to avoid sending data externally. Now they're discovering they have zero protection against prompt injection. Here's what's broken and what to do about it.