First reported · updated · 3 reports anthropic.com
Lead dispatch
First reported · updated · 3 reports embracethered.com
AWS Kiro: Arbitrary Code Execution via Indirect Prompt Injection
Researchers found a vulnerability (CVE-2026-10591) in AWS Kiro, an agentic IDE, where hidden instructions planted in a web page or source file that Kiro processes can trigger indirect prompt injection to rewrite Kiro's own MCP server configuration (~/.kiro/settings/mcp.json) or allowlist arbitrary Bash commands in .vscode/settings.json, achieving arbitrary code execution on the developer's machine with no approval prompt. The human-in-the-loop approval boundary is bypassed because Kiro can write to these config files without user consent, and AWS has issued a fix and CVE.indirect-prompt-injection · prompt-injection · remote-code-execution · tool-abuse · config-poisoning
ai-agents · mcp · llm · agentic-ide
Severity
0.85
The wire · latest
First reported google.com
Staying Ahead of Adversarial AI Through Agentic Source Code Review | Google Cloud Blog
Mandiant (Google Cloud) describes its Agentic Vulnerability Discovery Harness (AVDH), a multi-agent orchestration framework built on Google's Agent Development Kit that uses Gemini plus human expert-driven validation to find exploitable vulnerabilities in source code during proactive reviews, pentests, red-team ops, and incident response. Over 10 months it reportedly analyzed tens of millions of lines of code, generated tens of thousands of findings, and led to 12 assigned CVEs (e.g., CVE-2026-13242, CVE-2026-55803), including discovering 100+ critical bugs in stolen repositories in two days. Details →First reported nhimg.org
AI agent discovery of XXE in APIs: what it means for security teams
NHIMG editorial, based on a blog by Equixly, describes how an autonomous AI agent reasoned its way to discovering an XXE flaw from an OpenAPI spec, confirmed it out-of-band, and chained it to local file reads, SSRF, and recovery of a cleartext database password. The write-up argues that API security testing now depends on reasoning about application behaviour rather than payload coverage alone, and offers guidance on auditing transformation points, adding out-of-band confirmation, and disabling dangerous XML parser defaults. Details →First reported projectblack.io
Local AI for Penetration Testing & Research
A researcher benchmarked four approaches for discovering a known authenticated LFI vulnerability (CVE-2026-12194 in PHPIPAM): Semgrep, the agentic Strix pentest agent with GLM 5.1, a cloud SOTA model with a code-review skill, and a local AI model with a custom harness. Only the local AI + custom harness reliably found the bug, with the author concluding that the harness/approach matters more than the underlying model, while the Strix agent consumed ~60 million tokens over ~12 hours without success. Details →First reported aona.ai
AI Agents Are Finding Zero-Days Faster Than Security Teams Can Govern Them
An Aona AI blog post analyzes how autonomous AI security agents are discovering zero-days at unprecedented speed, citing a startup that reported 21 previously unknown FFmpeg vulnerabilities with reproducible PoCs for about $1,000 of compute, and Google patching a record 429 Chrome bugs after adapting its bounty program to a flood of AI-generated reports. The piece argues the bottleneck has shifted from discovery to validation, governance, and trust in AI-generated findings. Details →First reported anthropic.com
Disclosed CVEs: 3.5× Spike After Claude Mythos | Epoch AI
Epoch AI reports a more-than-3.5x spike in high- and critical-severity CVE disclosures (around 1,500 in June 2026) from 21 major organizations, correlated with Anthropic's April 2026 announcement that Claude Mythos Preview can autonomously discover and exploit software vulnerabilities. Anthropic's Project Glasswing and OpenAI's Daybreak have used frontier models to find and fix bugs, with Glasswing claiming over 10,000 high/critical vulnerabilities identified. Details →How the wire is made
Poll & cluster
Internet is crawled for AI security news and near-duplicate coverage is embedded and grouped into durable items.
Curate
AI Agent filters for agentic-AI relevance, classifies and tags each item, scores severity for threats, and writes the summary.
Every item here is one machine-curated intelligence object, not a headline.
Read the wire for free. There is a small charge to ask the index questions.
The wire, open
The complete curated feed, no key required.
- GET /feed.xml — RSS 2.0, every item
- GET /api/items — read-only
The vector desk
Query the index by meaning, not just keyword.
- GET /api/items?tags=&minSeverity=&itemType=
- GET /api/search?q= — keyword
- GET /api/semantic?q= — vector