Jira

Jira Is Turing-Complete

AgentRedBench: Dynamic Redteaming and Integration-Aware Defense for LLM Agents over SaaS Integrations

Announce Type: new Abstract: Indirect prompt injection in tool-use agents is a concrete production threat: LLM agents read from integrations (third-party services such as Gmail, Salesforce, or Jira accessed through tool calls) whose response content the user neither writes nor controls. Existing benchmarks under-measure the threat: most cover only a handful of integrations with the same attack payload replayed across runs, and open-source guards are trained on chat-style data rather than...

AgentRedBench: Dynamic Redteaming and Integration-Aware Defense for LLM Agents over SaaS Integrations

arXiv:2606.02240v2 Announce Type: replace Abstract: Indirect prompt injection in tool-use agents is a concrete production threat: LLM agents read from integrations (third-party services such as Gmail, Salesforce, or Jira accessed through tool calls) whose response content the user neither writes nor controls. Existing benchmarks under-measure the threat: most cover only a handful of integrations with the same attack payload replayed across runs, and open-source guards are trained on...

Ask HN: What are tools you have made for yourself since the advent of AI?

I've made a number of ceramic molds for slumping fused glass into bowls. As well as wooden templates for ceramic mugs. I've devised a few carrying tools to move glass frit paintings from my studio down to my barn where the kilns sit without spilling the glass.

Snowflake buys Natoma to help freeze out rogue agents

Snowflake is acquiring Natoma, a startup that provides a gateway for managing AI agent permissions across enterprise applications. This acquisition is part of Snowflake's strategy to establish an "agentic control plane," ensuring that AI agents can interact with business systems while adhering to strict security and governance policies. Natoma's technology enforces identity verification and access controls at the level of individual tool calls, allowing for secure and controlled AI actions.

Okta writes its own license to kill rogue AI agents

Rogue agents are dangerous, but eliminating them is never easy. Jason Bourne, Ethan Hunt, and James Bond have each run afoul of their governance at various junctures, yet stopping them takes sequel after sequel until all the loose ends are tied up and they eventually die or retire, only to get rebooted. It’s not so different in the world of AI agents.

9 Mothers (YC P26) Is Hiring

[ CAREERS · 9 MOTHERS ] · 12 open roles Build counter-drone systems in Austin. We ship hardware on software tempo — AI perception, kinetic engagement, and the kill chain that closes them. Hard problems, real deployment, short iteration loops, and the people doing the work own the spec.