LLM Security, Prompt Injection & AI Incidents · 454 Artikel
AI agents are moving through enterprise environments, inheriting permissions, traversing systems, and executing decisions at machine speed with minimal oversight. The identity infrastructure built to govern human access wasn't designed for autonomous actors, and the gap between what enterprises are...
Anthropic appears to be testing Claude Cowork support on mobile, allowing you to manage long-running Claude tasks from your phone. [...]
A newly discovered macOS malware dubbed "Gaslight" is designed to confuse AI-assisted malware analysis tools by hiding prompt injection strings and fake debugging data within the executable. [...]
This is a fascinating explotation of how LLMs fall for prompt injection attacks. It turns out that they learn to recognize the style of text in different role/instruction blocks, and not just the tags. Their conclusion: Role tags were a formatting trick that became the security architecture and the...
Kaspersky researchers analyze the threat landscape for SMBs in 2026: the rise of attacks involving fake AI tools, phishing schemes, and data sold on the dark web.
A previously undocumented Rust-based macOS implant and information stealer has been found to embed a prompt injection payload designed to trick a malware analyst's artificial intelligence (AI) tools and trick it into aborting or refusing an analysis of the artifact. The malware has been codenamed...
Queens District Attorney Melinda Katz announced that Jonathan Rinaldi has been charged with forgery and criminal possession of a forged instrument for allegedly creating and distributing false political endorsements and fake news articles u ... (https://incidentdatabase.ai/cite/1557#7455)
An X user managed to trick AI chatbot Grok into sending around $200,000 worth of crypto after exploiting its link with an automated trading bot. The incident involved Grok and 'Bankrbot', two AI systems with wallet access, which were manip ... (https://incidentdatabase.ai/cite/1556#7454)
A partner at Boies Schiller Flexner is seeking to file a corrected brief in litigation against the Church of Scientology after taking responsibility for "material citation errors" that it contained. In a Sept. 19 declaration, partner John ... (https://incidentdatabase.ai/cite/1555#7453)
LONDON, June 5 (Reuters) - Last Christmas Eve, NewsBreak, opens new tab, a free app with roots in China that is the most downloaded news app in the United States, published an alarming piece about a small town shooting. It was headlined "Ch ... (https://incidentdatabase.ai/cite/1554#7451)
From hidden content injections to cognitive state poisoning, attackers are turning trusted data sources into traps for autonomous AI. The post When Information Becomes the Attack Surface – Understanding AI Agent Traps appeared first on SecurityWeek.
Context is the central plank of AI in general, and agentic AI in particular. If an AI system doesn’t have the correct context, it cannot make the correct decisions. The post Agentic AI Security: Wrong Context, Wrong Decisions at Machine Speed appeared first on SecurityWeek.
1\. Introduction Fletcher v. Experian Info Solutions is an appellate sanctions decision arising from a Fair Credit Reporting Act dispute in which the Fifth Circuit confronted a rapidly recurring litigation risk: the use of generative artif ... (https://incidentdatabase.ai/cite/1453#7449)
In Fletcher v. Experian Information Solutions, Inc., the U.S. Court of Appeals for the Fifth Circuit sanctioned a lawyer $2,500 for filing a reply brief with several "hallucinated" case citations and then providing evasive responses to the ... (https://incidentdatabase.ai/cite/1453#7448)
The Fifth Circuit recently issued a sharp warning to lawyers who use generative AI in federal appellate practice. In Fletcher v. Experian Information Solutions, Inc. (opinion below), the court sanctioned appellate counsel after finding that ... (https://incidentdatabase.ai/cite/1453#7447)
Executive Summary: A video circulating on social media falsely claims that India's Finance Minister, Smt. Nirmala Sitharaman, has endorsed an investment platform promising unusually high returns. Upon investigation, it was confirmed tha ... (https://incidentdatabase.ai/cite/1553#7446)
The Sixth Circuit's recent decision in Whiting v. City of Athens, 2026 U.S. App. LEXIS 7479, is a significant ruling addressing attorney misconduct, particularly the submission of fabricated legal citations and misrepresentations in appella ... (https://incidentdatabase.ai/cite/1447#7445)
The Sixth Circuit finally weighed in on the use of fake cases hallucinated by artificial intelligence. A panel recently sanctioned two Tennessee attorneys for a smorgasbord of misconduct during merits briefing, including citing fake cases. ... (https://incidentdatabase.ai/cite/1447#7444)
GLENDALE, AZ (AZFamily) --- An AI system used to read graduate names at Glendale Community College's commencement ceremony malfunctioned, leaving students and families frustrated. The names being read during GCC's commencement didn't appea ... (https://incidentdatabase.ai/cite/1503#7443)
Much of the public debate around generative AI has focused on human-centered content: political deepfakes, manipulated speeches, fabricated celebrity videos, and non-consensual intimate imagery. This focus is justified given the scale, seve ... (report_number: 7442)
ST. PETERSBURG, Fla. --- A couple in St. Petersburg is scammed out of nearly two thousand dollars in bogus vet bills. They say they fell for it because the scammers took pictures of a lost dog posted online and sent the couple an AI-genera ... (https://incidentdatabase.ai/cite/1477#7441)
AUGUSTA --- A Belfast man who killed his wife and assaulted his mother with a fire poker in Readfield was deemed not criminally responsible for those acts Thursday. He was ordered held by the state in a psychiatric hospital over the objecti ... (https://incidentdatabase.ai/cite/1491#7440)
The CI/CD workflow weakness affects Microsoft's Azure Sentinel, Google's AI Agent Development Kit, Apache's Doris analytics database, Cloudflare's Workers SDK, and Python Software Foundation's Black.
Security firm AIR built a fake AI agent skill, pushed it through a popular skill marketplace and an Instagram ad, and says it reached roughly 26,000 agents, including some on corporate accounts. Every skill security scanner the firm tested it against marked it safe. The payload was harmless by...
OpenAI on Monday said it's releasing an improved version of its GPT‑5.5‑Cyber model to trusted defenders as part of the Daybreak initiative, the artificial intelligence (AI) company announced last month. Calling GPT‑5.5‑Cyber its "strongest model yet for finding and helping patch software...
A driver in a Tesla vehicle that was engaged in automated driver-assistance mode crashed into a house in Texas on Friday night and killed a woman inside, the authorities said. The driver, Michael Butler, was in a Tesla Model 3 about 8 p.m. ... (https://incidentdatabase.ai/cite/1552#7439)
President Trump's use of Japanese anime-style imagery on his social media account has not gone over well in Japan. The Japanese government on Friday criticized Mr. Trump's use of Japanese companies' intellectual property, with a top minist ... (report_number: 7438)
Waymo has restricted freeway rides while it works on a software fix for nearly 3,900 robotaxis after some of its driverless vehicles entered freeway construction zones in Phoenix and the Bay Area, according to federal safety records. The v ... (https://incidentdatabase.ai/cite/1547#7437)
Waymo has filed its fourth safety recall since February 2024, after its driverless cars were caught entering closed freeway-construction zones. The recall, filed with the National Highway Traffic Safety Administration (NHTSA) on June 17, a ... (https://incidentdatabase.ai/cite/1547#7436)