Skip to content

What changed in AI security, Jul 6 to Jul 12, 2026

Jul 6 to Jul 12, 2026 (ISO week 2026-W28). Weeks run Monday to Sunday in UTC.

158 records published, +23 on the previous week: 43 vulnerabilities (+6), 0 incidents (no change), 10 research items (-2), 103 news items (+17), 2 policy items (+2).

Critical and high advisories

Vulnerability records rated critical or high, newest first. Showing 25 of 27.

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-2026-59822: LiteLLM authentication bypass through MCP Streamable HTTP endpoint
CVE-2026-59822NVD/CVE Database
Known exploited0.8%
CVE-2026-61447: PraisonAI remote code execution in CodeAgent._execute_python()
CVE-2026-61447NVD/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
opentelemetry-instrumentation-genai-anthropicPyPIAnthropic SDK1.0b0
opentelemetry-instrumentation-genai-openaiPyPIOpenAI SDK1.0b0
lfx-exaPyPILangChain0.1.0

Topics that moved

Largest increases over the mean of the 4 previous weeks, for topics with at least 3 records in the week.
TopicRecordsWeekly mean, previous 4Difference
AI agents3216.0+16.0
Prompt injection and jailbreaks123.8+8.3
Inference infrastructure43.5+0.5

Research

Peer-reviewed first, then newest. Showing 8 of 10.

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