What changed in AI security, May 19 to May 25, 2025
May 19 to May 25, 2025 (ISO week 2025-W21). Weeks run Monday to Sunday in UTC.
9 records published, +5 on the previous week: 5 vulnerabilities (+3), 0 incidents (no change), 0 research items (no change), 3 news items (+1), 1 policy item (+1).
Critical and high advisories
Vulnerability records rated critical or high, newest first.- Critical
CVE-2025-47277: vLLM PyNcclPipe KV cache transfer exposed on all network interfaces
CVE-2025-47277NVD/CVE Database - Critical
CVE-2025-46725: Langroid LanceDocChatAgent code execution via pandas eval
CVE-2025-46725NVD/CVE Database - Critical
CVE-2025-46724: Langroid TableChatAgent code injection through pandas eval()
CVE-2025-46724NVD/CVE Database - High
CVE-2025-2099: transformers preprocess_string ReDoS through crafted docstring input
CVE-2025-2099NVD/CVE Database
Exploitation signals
Vulnerabilities published in the week that are listed in the CISA Known Exploited Vulnerabilities catalog or have an EPSS score of 10% or more.No vulnerability published in this week is listed as exploited or has an EPSS score of 10% or more.
Packages that began delegating to a language model
Exposure Registry packages whose first release declaring an LLM SDK, agent framework or MCP dependency was published in the week.No tracked package published its first release with an LLM SDK, agent framework or MCP dependency in this week.
Topics that moved
Largest increases over the mean of the 4 previous weeks, for topics with at least 3 records in the week.No topic had at least 3 records in this week and more than its mean over the 4 previous weeks.
Research
Peer-reviewed first, then newest.No research papers or reports were published in this week.
Policy and regulation
Newest first.Generated from the AI Sec Watch database at . Every item links to its record.