arXiv OverEager — coding agents exceed authorized scope on benign tasks
New arXiv paper quantifies overeager actions in coding agents like Claude Code, Codex CLI, and Gemini CLI on harmless tasks.
Posts
High-signal AI/security/automation notes.
Filter: All AI Vulnerabilities & CVEs (264)Tools & Comparisons (2)AI Security Research (198)Agent & Supply Chain Security (662)
Aikido Security — Laravel-Lang supply chain delivers cross-platform credential stealer
Over 233 malicious versions of popular Laravel-Lang PHP packages were injected with a credential-stealing backdoor via poisoned GitHub version tags targeting developer infrastructure.
LMDeploy CVE-2026-46517 — hardcoded trust_remote_code bypasses HF default-secure
MDPI — attack surfaces of malicious remote MCP servers across LLM platforms
New MDPI paper categorizes MCP server attack surfaces into LLM-passive and LLM-active frameworks across multiple platforms.
NVIDIA OpenShell — open-source secure sandboxed runtime for AI agents
NVIDIA open-sources OpenShell, a sandboxed execution runtime for autonomous AI agents with declarative YAML policy enforcement.
arXiv — ASPI Shows Clarification-Seeking Amplifies Prompt Injection in LLM Agents
New benchmark reveals that asking agents to seek clarification before acting increases prompt injection success from ~2% to ~35% across frontier models.
arXiv — Domain-Camouflaged Prompt Injections Evade LLM Injection Detectors
New paper shows injection detectors drop from 93.8% to 9.7% detection when payloads mimic target-domain vocabulary, revealing a systemic blind spot in multi-agent LLM security.
CISA Adds Langflow Origin Validation Flaw to KEV — Active Exploitation Confirmed
CISA added CVE-2025-34291, a critical origin validation error in the Langflow AI builder platform, to its Known Exploited Vulnerabilities catalog with a CVSS score of 9.4.
Google Threat Intel — LLM-Generated Morphing Malware and Automated Vulnerability Discovery
Splunk AI Toolkit — CVE-2026-20238 Improper Access Control
Splunk patches three vulnerabilities in its AI Toolkit, including CVE-2026-20238 allowing low-privilege attackers to bypass role-based access control and trigger DoS conditions.
TeamPCP — 20-Wave Supply-Chain Campaign Hits 500+ Tools, GitHub
Trump Scraps AI Executive Order on Frontier Model Oversight
Trump abruptly postponed a planned AI executive order that would have required pre-deployment government review of frontier models, after pressure from tech leaders.
WordPress 7.0 — AI Agent Infrastructure and API Key Theft Risk
WordPress 7.0 ships AI client, Connectors API, Abilities API, and an MCP adapter, centralizing high-value API keys across 43% of the web.
arXiv: AI Agents May Always Fall for Prompt Injections
New arXiv paper recasts prompt injection through Contextual Integrity theory, demonstrating an impossibility result: any defense tight enough to block attacks will also break legitimate agent workflows.
arXiv — Securing LLM Agents Needs Intent-to-Execution Integrity (2605.16976)
NUS/UCLA/Berkeley researchers propose intent-to-execution integrity as a correctness property for LLM agent security, analyzing defense gaps in systems like OpenClaw, NemoClaw, and SeClaw.
arXiv: Remembering More, Risking More — Longitudinal Safety in Memory Agents
New arXiv paper shows memory-equipped LLM agents accumulate risk over time as stored content contaminates future decisions, even across unrelated tasks.
CSA Research Note: MCP Security Crisis — Systemic Design Flaws in AI Agent Infrastructure
Nebula Security — Vega AI Discovers nginx-poolslip Zero-Day RCE in Patched nginx 1.31.0
An autonomous AI security agent Vega found a second unpatched RCE in nginx 1.31.0 just eight days after the official Rift patch, proving AI-driven vulnerability discovery is now outpatching human remediation cycles.