Posts

High-signal AI/security/automation notes.

Filter: All AI CVEs (44)Tool Comparisons (2)Research (38)Security (107)

Pen Test Partners — Eurostar chatbot guardrail bypass + ID tampering

2026-01-31 Security

Snyk — Clawdbot/Moltbot prompt injection: ‘one email away from disaster’

2026-01-31 Security

GitHub Advisory — vLLM DoS via 1×1 image (CVE-2026-22773)

2026-01-31 AI CVEs

GitHub Advisory — vLLM multimodal SSRF (CVE-2026-24779)

2026-01-31 AI CVEs

vLLM — Mixture-of-Models routing on AMD GPUs (vLLM-SR)

2026-01-31 Research

Wiz — ZeroDay.cloud: cloud + AI infra zero-days

2026-01-31 Security

arXiv/EACL — PHISH: persona jailbreaking via implicit steering in chat history

2026-01-30 Research

arXiv — From prompt injections to protocol exploits

2026-01-30 Research

arXiv — SoK: prompt injection attacks on agentic coding assistants

2026-01-30 Research

arXiv — Thought-Transfer: clean-label poisoning via chain-of-thought traces

2026-01-30 Research

AWS/Wiz — CodeBreach: unanchored ACTOR_ID filters in CodeBuild webhooks

2026-01-30 Security

Bitdefender — Hugging Face abused to distribute polymorphic Android RAT payloads

2026-01-30 Security

Bizarre Bazaar: attackers monetizing exposed LLM & MCP endpoints (LLMjacking)

2026-01-30 Security

Operation ‘Bizarre Bazaar’: LLMjacking campaign targets exposed LLM/MCP endpoints (Pillar Security)

2026-01-30 Security

arXiv — Cascaded vulnerability attacks in software supply chains (ICSE 2026 EA)

2026-01-30 Research

CISA/NCSC-UK/FBI — Secure connectivity principles for OT networks

2026-01-30 Security

Cisco Security Blog — Foundation AI’s push for agentic security systems

2026-01-30 Security

curl — Ending its bug bounty after an AI slop flood

2026-01-30 Security

Cyata — Prompt-injection reachable CVEs in Anthropic’s official Git MCP server

2026-01-30 AI CVEs

Fortinet — FortiCloud SSO auth bypass exploited in the wild (CVE-2026-24858)

2026-01-30 AI CVEs