AI Beyond Identity

AI agent refusals in security testing: what changes for teams now

First post and replies  | Last post by Mr NHI, 4 weeks ago

RAG poisoning and the retrieval trust gap for AI systems

First post and replies  | Last post by Mr NHI, 4 weeks ago

AI coding agents and MCP security: what controls are missing?

First post and replies  | Last post by Mr NHI, 4 weeks ago

AI agents in observability workflows: are your controls keeping up?

First post and replies  | Last post by Mr NHI, 4 weeks ago

Financial AI agent drift: are your controls catching behavior, not just transactions?

First post and replies  | Last post by Mr NHI, 4 weeks ago

AI agent production readiness: are your evals keeping up?

First post and replies  | Last post by Mr NHI, 4 weeks ago

RAG testing: are retrieval and generation being measured separately?

First post and replies  | Last post by Mr NHI, 4 weeks ago

Agentic code hooks and the governance gap teams are missing

First post and replies  | Last post by Mr NHI, 4 weeks ago

Direct vs indirect prompt injection: where does the split stop mattering?

First post and replies  | Last post by Mr NHI, 4 weeks ago

AI agent data exposure: what IAM and compliance teams need to know

First post and replies  | Last post by Mr NHI, 4 weeks ago

AI agent attack surfaces: what identity teams need to know

First post and replies  | Last post by Mr NHI, 4 weeks ago

Long-horizon agent evals: are fixed LLM judges still enough?

First post and replies  | Last post by Mr NHI, 4 weeks ago

Claude Opus 5 and appsec: what changes when code finding improves?

First post and replies  | Last post by Mr NHI, 4 weeks ago

AI red teaming benchmarks: are your guardrails hiding silent failures?

First post and replies  | Last post by Mr NHI, 4 weeks ago

AI agents and grounded context: can graphs replace repeated code reads?

First post and replies  | Last post by Mr NHI, 4 weeks ago

EU AI Act deadlines shifted, but what changes for practitioners?

First post and replies  | Last post by Mr NHI, 4 weeks ago

MCP security and AI connectors: what are teams missing?

First post and replies  | Last post by Mr NHI, 4 weeks ago

AI chatbot red teaming: why multi-agent testing matters now

First post and replies  | Last post by Mr NHI, 4 weeks ago

Agent trajectory metrics: what should security teams measure now?

First post and replies  | Last post by Mr NHI, 4 weeks ago

AI teammate memory and blast radius: what IAM teams should watch

First post and replies  | Last post by Mr NHI, 4 weeks ago