Skip to content
AI Sec Watch

What changed in AI security, Jul 27 to Aug 2, 2026

Jul 27 to Aug 2, 2026 (ISO week 2026-W31). Weeks run Monday to Sunday in UTC.

193 records published, -3 on the previous week: 21 vulnerabilities (-28), 0 incidents (-2), 3 research items (-14), 167 news items (+39), 2 policy items (+2).

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.
All packages
PackageEcosystemLLM SDKsReleaseReleased
genkit-vertexaiPyPIAnthropic SDK, Genkit, Google Gemini SDK, Google Vertex AI SDK0.9.0
genkit-openaiPyPIGenkit, OpenAI SDK0.9.0
genkit-ollamaPyPIGenkit, Ollama client0.9.0
genkit-middlewarePyPIGenkit0.9.0
genkit-google-cloudPyPIGenkit0.9.0
genkit-flaskPyPIGenkit0.9.0
genkit-fastapiPyPIGenkit0.9.0
genkit-evaluatorsPyPIGenkit0.9.0
genkit-djangoPyPIGenkit0.9.0
genkit-anthropicPyPIAnthropic SDK, Genkit0.9.0
lfx-datastaxPyPILangChain0.1.3
@ai-sdk/minimaxnpmVercel AI SDK0.0.0

Topics that moved

Largest increases over the mean of the 4 previous weeks, for topics with at least 3 records in the week.
All topics
TopicRecordsWeekly mean, previous 4Difference
AI agents4224.5+17.5
Frontier model safety60.8+5.3
AI regulation and standards30.0+3.0
Robotics and embodied AI30.3+2.8
Deepfakes and impersonation31.3+1.8

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