Varonis disclosed a flaw in Microsoft Copilot Personal, the consumer assistant, that could let a single click exfiltrate data from connected apps, and the way they found it is striking. Tracked as CVE-2026-24301 and named CoSnitch, the technique had the researchers repeatedly ask Copilot why a prompt could not run without user interaction; each refusal added a technical justification, until the assistant named a hidden parameter, the exact session conditions where it worked, and the protections meant to block it. Building the request as described, the bypass ran. Varonis said Copilot was not breached but played. Related research showed attacker pages persisting unwanted memory in Copilot through indirect prompt injection.
Two security firms showed that Atlassian's Rovo AI assistant can be steered by hidden instructions into collecting Jira and Confluence data a signed-in user can access and sending it to an outside server. PromptArmor concealed the instructions in a document Rovo reads, so asking it to organize tickets makes it gather internal data and leak it through a URL request, with no approval step and even with web search disabled. Varonis used a chat URL parameter to preload instructions, so one click ran them with the user's privileges. Atlassian fixed the link-based path server-side, but the content-based path was not confirmed fixed at disclosure.
Microsoft is warning that attackers can hijack AI agents through poisoned tool descriptions, the plain-text notes that tell an agent what a tool does. Because agents connect to systems through the Model Context Protocol and read these descriptions to decide how to act, an attacker who updates a trusted third-party tool can bury a hidden instruction in its description, telling the agent to quietly collect and exfiltrate data on its next task. Many setups pick up description changes without re-approval, so the poisoned version goes live silently. Each step the agent takes looks legitimate and runs with the user's own permissions, so no alarm fires.
Researchers at Varonis disclosed SearchLeak, a flaw chain in Microsoft 365 Copilot Enterprise Search that let a single click on a legitimate microsoft.com link silently pull a victim's emails, calendar, and indexed files, including security and MFA codes, with no password or further interaction. It worked by smuggling instructions into the search URL's query parameter, which Copilot obeyed as commands, then exfiltrating the data through a Bing image request that bypassed content protections. Because the link used a real Microsoft domain, anti-phishing filters were unlikely to flag it. Microsoft assigned CVE-2026-42824, rated it critical, and fixed it on its backend, so no customer action is required.
West Pharmaceutical Services - the Pennsylvania-based S&P 500 maker of injectable pharmaceutical packaging and drug delivery components, with annual revenues over $3 billion and 10,800 employees - filed an SEC 8-K disclosing a 'material cybersecurity attack.' The company detected the intrusion on May 4, 2026, and confirmed on May 7 that attackers had exfiltrated data and encrypted certain systems. West took infrastructure offline globally for containment, engaged Palo Alto Networks' Unit 42 for forensics, and partially restored core enterprise, shipping, and manufacturing systems by May 13. No ransomware group has publicly claimed the attack, and West says it has 'taken steps intended to mitigate the risk of dissemination of the exfiltrated data.'
Socket researchers found more than 150 RubyGems packages doing something the registry was never built to do: smuggling scraped data out of UK council websites. The malicious gems fetch pages from Lambeth, Wandsworth, and Southwark's public meeting portals, bundle the responses into a normal-looking .gem archive, and push it back to RubyGems using a hardcoded API key. The attacker then downloads the data as a public gem version. Whether GemStuffer is registry spam, a worm being tested, or a deliberate trial of package-registry abuse, the mechanics are intentional - and it landed the same week RubyGems froze new account signups over a separate flood of malicious packages.
TrustStrike Labs