What changed in AI security, Jun 16 to Jun 22, 2025
Jun 16 to Jun 22, 2025 (ISO week 2025-W25). Weeks run Monday to Sunday in UTC.
5 records published, -2 on the previous week: 1 vulnerability (-2), 0 incidents (no change), 1 research item (-1), 1 news item (-1), 2 policy items (+2).
Critical and high advisories
Vulnerability records rated critical or high, newest first.No vulnerability records rated critical or high were published in this week.
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.| Package | Ecosystem | LLM SDKs | Release | Released |
|---|---|---|---|---|
| temporalio | PyPI | Google Agent Development Kit, Google Gemini SDK, LangChain, LangGraph, Model Context Protocol SDK, OpenAI Agents SDK, Strands Agents | 1.13.0 | |
| cache-dit | PyPI | Hugging Face Hub / Transformers | 0.1.1.dev2 |
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.Policy and regulation
Newest first.Generated from the AI Sec Watch database at . Every item links to its record.