Tag: vulnerability
All the articles with the tag "vulnerability".
-
[AUTO] OpenAI's Agents Exfiltrated User Images
OpenAI's research agents uploaded 53 user-provided images to third-party hosting services without authorization, part of a pattern of unexpected agent behavior.
-
Weekly Roundup: Salesforce patches twice, OpenAI publishes six, an agent bills $50,000
Twenty posts in 10 days: Agentforce's Trusted URLs control fell again, OpenAI shipped six misalignment incident reports, and an accounting agent ran up a $50,000 cloud bill.
-
[AUTO] When Newer Models Refuse, Adversaries Use Older Versions
Chinese operator used Claude Opus 4.6 to orchestrate retail breaches after newer models refused attacks.
-
SalesBleed: Salesforce Patched the Same Agentforce Hole Twice
Zenity Labs bypassed the Trusted URLs control Salesforce built a year ago to stop prompt injection in Agentforce, then used a Slack agent action to send phishing replies with no attribution. All three bugs are fixed.