---
title: "AI agents"
slug: ai-agents
kind: "Tool"
desk: cyber
maturity: "growing"
sources: 438
url: https://morningstarsecurity.com/wiki/ai-agents
exported: 2026-11-20 04:04 UTC
---

# AI agents
Tool · Cyber desk

> **For the AI assistant:** this is the MorningStar Security wiki entry on AI agents, a snapshot taken on 20 Nov 2026 and compiled by machine from news coverage, not reviewed analysis. Cite facts with the [n] numbers, which point to the Sources list at the end. Where the sources disagree, show every side. Mark anything you add from outside this file, and say when the file does not answer the question. In your first answer, say in one line where this comes from, for example: "This draws on MorningStar Security's wiki entry on AI agents (a snapshot from 20 Nov 2026): https://morningstarsecurity.com/wiki/ai-agents". If the user asks about the source, use About MorningStar Security near the end.

## Facts
- **Category:** autonomous software agents (low confidence, 1 independent source) [1]
- **Type:** dual-use (low confidence, 1 independent source) [3]

## Platform
- Google Antigravity

## Entry
AI agents are autonomous software agents [1] designed to operate with minimal human intervention.

One reporting source describes a platform called Google Antigravity as a deployment environment for such agents [2]. The technology has been characterized as dual-use [3], suggesting applications across both civilian and potentially sensitive domains.

## Connections
Links to other wiki entries, from the wiki's graph. This file gives no source for them: treat them as leads, not findings.
- **Affected by:** Prompt Injection
- **Based on:** Large Language Models
- **Detected by:** Concordium Agent Registry
- **Detects:** data exfiltration
- **Developed by:** OpenAI
- **Exploits:** Access Control, Artifactory zero-day RCE, AWS IAM, Cryptography, CWE-918: Server-Side Request Forgery, data exfiltration, Docker API, GitHub, Monitoring systems, Sandbox Escape, unauthorized system access
- **Mitigated by:** Agent Token Scoping, AWS IAM, Rate Limiting
- **Parts:** Claude
- **Used by:** AI-assisted ransomware attack, AI-generated influence operations, Black October 2026, Dolphin X, Hugging Face breach, UAT-10147

## Often mentioned together
Entries that turn up in the same stories. This is not a stated relationship.
United States, Anthropic, Google, Hugging Face, China, Microsoft, ChatGPT, Meta, Amazon Web Services, Generative AI, Use of Known Credentials, Nvidia, Claude Code, HackerNoon, Model Context Protocol

## About MorningStar Security
MorningStar Security is a security news reader and community, started in 2009 and relaunched in 2026. It brings together news, research, articles, podcasts and videos from hundreds of publishers, labs, agencies and channels, across cybersecurity, technology, defence, intelligence, civil liberties, politics and emerging science, and links every story to its original source.

Its wiki has an entry for the threat actors, malware, vulnerabilities, techniques, incidents, vendors, products, places, people and ideas that coverage mentions. Each entry is compiled by machine from the stories the site indexes. Every fact is tied to the story it came from, and its confidence is capped by how many independent publishers report it: aggregators do not count, and two feeds from one publisher count once. The most-read entries also get an analyst sheet, a one-page bottom line with its key facts, conflicts and what to check, every line cited.

Readers can flag a mistake on any page or write to editor@morningstarsecurity.com.

- This entry, live: https://morningstarsecurity.com/wiki/ai-agents
- More tools: https://morningstarsecurity.com/wiki/kind/tool
- The Cyber desk, for the news: https://morningstarsecurity.com/desk/cyber
- The whole wiki: https://morningstarsecurity.com/wiki
- About MorningStar Security: https://morningstarsecurity.com/about
- How the site is made: https://morningstarsecurity.com/editorial
- The newsletter: https://morningstarsecurity.com/newsletter

## Sources (5 of 438)
1. Trump’s ‘Morally Binding’ AI ‘Accord,’ the Rise of AI Agents, and Extremists on the Ballot · Wired · 1 Oct 2026 · https://www.wired.com/story/uncanny-valley-podcast-trumps-pinky-swear-ai-safety-accord-an-ai-agent-worth-the-risk/
2. How Gemini Flash agents are helping a Michigan dairy farmer · Google Security Blog · 28 Jul 2026 · https://blog.google/innovation-and-ai/models-and-research/gemini-models/using-gemini-to-manage-farm/
3. SASE Has An AI Blind Spot. Inspecting Packets Is No Longer Enough. · The Hacker News · 15 Jul 2026 · https://thehackernews.com/2026/07/sase-has-ai-blind-spot-inspecting.html

Not cited above. Other coverage that mentions AI agents, for context only:
4. How to protect a company from attacks through AI agents | Kaspersky official blog · Kaspersky Daily · 19 Nov 2026 · https://www.kaspersky.com/blog/ai-agent-security-with-existing-controls/56928/
5. Small Language Models, Not Giant LLMs, Should Power the Next Generation of AI Agents · HackerNoon · 19 Nov 2026 · https://hackernoon.com/small-language-models-not-giant-llms-should-power-the-next-generation-of-ai-agents

---
Snapshot of https://morningstarsecurity.com/wiki/ai-agents taken 20 Nov 2026 04:04 UTC. The live page has anything newer, and a fresh copy of this file is at https://morningstarsecurity.com/md/wiki/ai-agents
