Skip to content

What changed in AI security, Jul 21 to Jul 27, 2025

Jul 21 to Jul 27, 2025 (ISO week 2025-W30). Weeks run Monday to Sunday in UTC.

11 records published, no change on the previous week: 10 vulnerabilities (+2), 0 incidents (no change), 1 research item (no change), 0 news items (-1), 0 policy items (-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.
AdvisoryExploitationEPSSPublished
CVE-2025-5120: huggingface/smolagents sandbox escape allowing remote code execution
CVE-2025-5120NVD/CVE Database
Not listed24.6%
CVE-2025-51471: Ollama cross-domain token exposure in WWW-Authenticate realm handling
CVE-2025-51471NVD/CVE Database
Not listed15.2%

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
voyageaiPyPIHugging Face Hub / Transformers, LangChain0.3.4

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.

No regulatory or policy records were published in this week.

Generated from the AI Sec Watch database at . Every item links to its record.

RSS feed of weekly changesPrevious week