Skip to content

Forem

# llmsecurity

👋 Sign in for the ability to sort posts by relevant, latest, or top.

RC

Apr 27

Engineering teams keep granting agents production database writes

#aiagents #llmsecurity #systemsengineering #agentarchitecture

8 min read

Cover image for I Built a Policy Drift Detector for LLM Agents. Here's What Four Versions Taught Me.

Tracks gradual policy erosion across turns

Apr 21

I Built a Policy Drift Detector for LLM Agents. Here's What Four Versions Taught Me.

#llmsecurity #security #python #opensource

6 min read

Cover image for The Three Layers Developers Miss When They “Swap Models” (And Why Proxy‑Routing Claude Code Breaks All of Them)

Narnaiezzsshaa Truong

Apr 24

The Three Layers Developers Miss When They “Swap Models” (And Why Proxy‑Routing Claude Code Breaks All of Them)

#llmsecurity #proxyarchitecture #claudecode #supplychainrisk

3 min read

Cover image for I Prompt Injected My Own GitHub README. Then I Built a Honeypot.

Ioan G. Istrate

Mar 17

I Prompt Injected My Own GitHub README. Then I Built a Honeypot.

#llmsecurity #promptinjection #api #django

17 min read

Billy

Mar 13

LLM Security Risks: Prompt Injection, Data Poisoning, and How to Defend Against Them

#llmsecurity #promptinjection #datapoisoning #aimodelsecurity

5 min read

Tiamat

Mar 10

The 73% Problem: Why Enterprise Prompt Injection Fixes Don't Work (And What Actually Does)

#llmsecurity #promptinjection #security #ai

6 min read

Gerardo Arroyo for AWS Community Builders

Mar 27

Amazon Bedrock Guardrails: Content Filters, PII, and Streaming

#aws #awsbedrock #aisafety #llmsecurity

10 min read

👋 Sign in for the ability to sort posts by relevant, latest, or top.