13 casos · pág. 1/1
Microsoft has warned that AI agents with access to enterprise systems can be manipulated through prompt injection, compromised inputs or shifts in task context. Agents do not need malicious intent to cause harm: their ability to read corporate data, invoke tools, approve transactions and talk to other agents widens exposure once untrusted…
Signals Corps sampled 217 million HTTP page responses from Common Crawl and found almost 8,000 sites communicating with AI agents through HTTP headers. Most of these headers were navigational pointers, but 30 sites attempted indirect prompt injection. Of those, 22 were little more than pranks, while others could plausibly affect a visitin…
A Salt Security report, State of Agentic AI and API Security 2H 2026, finds that 49.8% of surveyed organisations confirmed or suspected an AI agent took an unintended, unexpected or unauthorised action in the past year. The research combines a survey of 380+ security and technology professionals with Salt Labs production telemetry. Among …
Researchers documented in August 2026 that standard, as-designed Salesforce Agentforce features can be chained so an unauthenticated outsider reaches an internal agent's instructions. Email-to-Case and Web-to-Case turn inbound messages into case records, and a Flow passes that data into the agent prompt. The agent's reply then leaves thro…
F5 Labs published its November 2025 AI Security Insights, drawn from the Comprehensive AI Security Index (CASI) and Agentic Resistance Scoring (ARS). Anthropic models took the whole top tier of the CASI leaderboard (Claude Haiku 4.5 at 95.89, Claude Sonnet 4.5 at 95.86, Claude Sonnet 4 at 95.33), while the GPT-5 family slipped, with GPT-5…
ESET researchers observed the Russia-aligned group UAC-0099 embedding a decoy request for guidance on building a nuclear weapon in a comment inside a VBScript used in the early stages of an attack on a target in Ukraine. The comment was meant to trigger the safety guardrails of an LLM-powered code scanner so that it stops inspecting the f…
HiddenLayer researchers evaluated TypeSafe AI's Jev "System One" decision model, which returns probabilities and a confidence score instead of freeform text. They found it remains vulnerable to indirect prompt injection, contradicting claims that it cannot hallucinate or make type errors. Jev was manipulated into a clickjacking-style acti…
In late August 2026, Sekoia's TDR team observed an attacker compromise an unauthenticated Flowise honeypot (emulating v2.2.8). The attacker harvested stored credentials, tried to plant a malicious chatflow with a callback to 154.217.251.226, and used prompt injection to turn the LLM agent into an offensive analysis assistant. The activity…
Researchers at Hacktron disclosed a vulnerability chain in Cluely, an Electron-based AI assistant that reads the user's screen and microphone. They found it in July 2025 and published in February 2026. The main window had no will-navigate handler, so a link in the AI's markdown response could navigate the whole app to an attacker-controll…
F5 Labs assesses the security risks and rewards of Chinese open-weight LLMs (Qwen, GLM, Kimi, MiMo, MiniMax, DeepSeek). It finds that strong offensive and defensive cyber capability does not translate into consistent resistance to attack. Cited examples include Kimi K3 finding 19 vulnerabilities in Redis and GLM 5.2 being self-hosted by H…
This ESET blog post argues that AI is speeding up the threat landscape for SMBs, both by empowering threat actors and by widening the attack surface as businesses adopt AI faster than they govern it. The ESET SMB Cyber Readiness Index 2026 reports that 73% of SMBs are integrating AI, 40% lack a proper AI policy, and 45% suffered a cyberse…
ESET analysis describes a two-pronged risk for small and mid-size businesses (SMBs): AI agents create new paths into business systems, while attackers use AI to add speed and scale to established threats. Between March and May 2026, ESET scanned almost 900,000 unique agent skills from popular repositories and found more than 25,000 suspic…
MITRE released version 20 of its ATT&CK framework, expanding coverage of recent adversary tradecraft across the Enterprise, ICS and Mobile domains. Enterprise gains nine techniques and sub-techniques, including two prompt injection techniques (direct and indirect), abuse of an organization's own AI agents for data theft, poisoning of web …
