Daily, Wednesday 18 June 2025
Reconstructed on 19 November 2026 from archived source metadata.
From the editor
The editor's note for this issue is not available. The developments below were selected and ranked automatically from the sources listed.
Top developments
- 1
LangSmith Bug Could Expose OpenAI Keys and User Data via Malicious Agents
Cybersecurity researchers have disclosed a now-patched security flaw in LangChain's LangSmith platform that could be exploited to capture sensitive data, including API keys and user prompts. The vulnerability, which carries a CVSS score of 8.8 out of a maximum of 10.0, has been…
- 2
Toward Principled LLM Safety Testing: Solving the Jailbreak Oracle Problem
As large language models (LLMs) become increasingly deployed in safety-critical applications, the lack of systematic methods to assess their vulnerability to jailbreak attacks presents a critical security gap. We introduce the jailbreak oracle problem: given a model, prompt,…
- 3
Winter Soldier: Backdooring Language Models at Pre-Training with Indirect Data Poisoning
The pre-training of large language models (LLMs) relies on massive text datasets sourced from diverse and difficult-to-curate origins. Although membership inference attacks and hidden canaries have been explored to trace data usage, such methods rely on memorization of training…
Further reading, by topic
Advisories in this window
- 35 npm advisories35 critical
- 2 PyPI advisories2 moderate
- 1 crates.io advisory1 moderate
- 1 Hex advisory1 low
This edition
20 developments and 39 advisories in the window. Selection and order are automatic: how stories are placed and ranked.