First reported · updated · 15 reports redhat.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 securityonline.info
CVE-2026-35029 Exploited for Full Server Takeover
CVE-2026-35029, a critical broken access control flaw in the LiteLLM AI gateway (versions before 1.83.0, CVSS 8.8), is being actively exploited to read sensitive files and achieve full server takeover. Attackers abuse the unauthenticated /config/update route to point UI_LOGO_PATH at files like /app/.env or /proc/self/environ and retrieve their plaintext contents via /get_image, and can overwrite admin credentials and register malicious pass-through proxy routes to exfiltrate model API secrets. Honeypot telemetry recorded roughly 3,900 requests from 73 distinct IPs targeting admin routes; the fix is version 1.83.0. Details →First reported · updated · 4 reports hiflylabs.com
Model Denial of Service in LLM Deployments · LLM Security Review
An explainer on Denial of Wallet attacks against pay-per-token LLM endpoints, filed under OWASP LLM10:2025 Unbounded Consumption, describing how attackers abuse legitimately-exposed inference endpoints to run up unsustainable cost while keeping the service up. The piece contrasts it with LLMjacking (credential theft), enumerates vectors like request flooding, oversized inputs, and long reasoning chains, and recommends token/dollar-denominated limits, output caps, timeouts, per-identity budgets, and centralized enforcement via an AI gateway. Details →First reported · updated · 3 reports cveasyai.com
How Tailscale and Aperture mitigate the lethal trifecta for AI agents
Tailscale's blog explains the "lethal trifecta" for AI agents—access to private data, exposure to untrusted content, and the ability to communicate externally—and argues that combining all three exposes agents to prompt-injection-driven data exfiltration. The post describes how an AI gateway (Aperture) can mitigate the trifecta by controlling agent permissions and external communication rather than relying on model guardrails alone. Details →First reported paloaltonetworks.com
Token Jacking: Cybercriminals Could Be Stealing Your AI Resources
Unit 42's "Token Jacking" report describes how cybercriminals steal AI API keys and abuse AI gateways to hijack victims' AI resources (LLMjacking-style abuse), running up costs and consuming compute on the victim's account. The write-up is categorized as malware and threat research covering the theft and misuse of AI tokens and credentials. Details →First reported embracethered.com
LLM Heist: Hijacking LiteLLM for Traffic Interception, Key Theft, and Tool-Call Injection
Security research from embracethered.com details red-team TTPs for hijacking LiteLLM, a popular AI gateway, to intercept LLM traffic, steal backend provider keys, perform unauthorized inference on the victim's account, and inject forged responses and tool calls downstream of the model. The technique leverages documented gateway-management functionality after compromising an instance via known LiteLLM flaws, including a March 2026 compromised PyPI credential stealer and an Obsidian Security-disclosed privilege-escalation/RCE. Details →First reported redhat.com
CVE-2026-49468 - Red Hat Customer Portal
CVE-2026-49468 is an Important-severity (CVSS 8.1) authentication-bypass flaw in LiteLLM, a proxy server (AI Gateway) used to call LLM APIs. A remote attacker sending a crafted Host header can bypass the proxy authentication layer to gain unauthenticated access to protected management routes, potentially leading to full system compromise. The issue is fixed in LiteLLM v1.84.0 (GHSA-4xpc-pv4p-pm3w), and Red Hat notes its default images do not start the vulnerable proxy. Details →First reported · updated · 3 reports darktrace.com
Hackers Compromise AWS AI Gateway Connected to Amazon Bedrock to Deploy XMRig Cryptominer
Darktrace disclosed an incident in which attackers compromised an AWS EC2 instance running LiteLLM-Proxy — an AI gateway centralizing access to Amazon Bedrock foundation models through a privileged IAM role — and deployed XMRig cryptomining malware. The instance had SSH port 22 exposed to all inbound traffic (0.0.0.0/0) and was hit by brute-force attempts, primarily from IP 145.241.123[.]102. Details →First reported nist.gov
NVD - CVE-2026-59819
CVE-2026-59819 is a vulnerability in LiteLLM, an AI gateway/proxy for calling LLM APIs, where prior to version 1.83.10-stable the /health/test_connection endpoint resolved request-supplied environment and OIDC file references in litellm_params, allowing a privileged caller to read arbitrary local files via an oidc/file/ reference (CWE-73). The issue is fixed in version 1.83.10-stable. Details →First reported github.com
GitHub - manojmallick/gavio: The open standard AI gateway — PII protection, audit, reliability & cost control as composable interceptors. Same API in Python, Java & JavaScript.
Gavio is an open-source AI gateway that adds PII protection, audit logging, reliability and cost control as composable interceptors, with a consistent API across Python, Java and JavaScript. It sits in front of LLM providers to inspect and mediate requests/responses. 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