First reported arxiv.org
Analysis · latest
First reported medium.com
AutoJack: The New Vulnerability Class Letting a Single Webpage Hijack Your AI Agent | by Raj Namdev | CodeToDeploy
A Medium write-up describes AutoJack, a named vulnerability class in which a single malicious webpage embeds content that hijacks an AI browsing agent's reasoning during a normal task (summarizing, price-checking, form-filling) and redirects it to execute the attacker's instructions with no user click, download, or approval. The piece frames it as a recently demonstrated form of indirect prompt injection against AI browsing agents. Details →First reported spellbook.com
AI Agent Hijacking: Risks, Examples, and Legal Implications
Spellbook, a legal AI vendor, published an explainer on "AI agent hijacking," describing how autonomous legal AI assistants can be manipulated via prompt injection hidden in client documents, stolen credentials, or command overrides to leak confidential data. The piece outlines legal and regulatory risks for law firms and suggests mitigations like access controls, monitoring, encryption, and staff training. Details →First reported nhimg.org
AI agents in the browser: what it means for IAM controls
An NHIMG editorial based on Surf Security content argues that AI agents which browse, log in, and act across SaaS and admin portals create machine-speed risk when they run in unmanaged browsers, leaving excessive permissions, persistent credentials, and limited auditability. It recommends treating the browser as an enforcement boundary and separating credential handling from agent logic to govern where agents may execute. Details →First reported thehackernews.com
Stop Your Legacy Infrastructure from Hijacking Your AI Agents
A conference talk recap discussing how attackers may use legacy infrastructure to circumvent AI security programs and hijack AI agents, noting rapid AI agent adoption outpacing security controls. 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