Skip to content

What changed in AI security, Jul 14 to Jul 20, 2025

Jul 14 to Jul 20, 2025 (ISO week 2025-W29). Weeks run Monday to Sunday in UTC.

11 records published, -3 on the previous week: 8 vulnerabilities (-4), 0 incidents (no change), 1 research item (no change), 1 news item (no change), 1 policy item (+1).

Critical and high advisories

Vulnerability records rated critical or high, newest first.

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.
PackageEcosystemLLM SDKsReleaseReleased
@brave/brave-search-mcp-servernpmModel Context Protocol SDK1.3.1
any-llm-sdkPyPIAnthropic SDK, Azure AI Inference / Azure OpenAI SDK, Cohere SDK, Google Gemini SDK, Groq SDK, Hugging Face Hub / Transformers, Mistral AI SDK, Ollama client, OpenAI SDK, Together AI SDK, xAI SDK0.0.1

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.

RSS feed of weekly changesPrevious week