What changed in AI security, Sep 8 to Sep 14, 2025
Sep 8 to Sep 14, 2025 (ISO week 2025-W37). Weeks run Monday to Sunday in UTC.
9 records published, -2 on the previous week: 8 vulnerabilities (-2), 0 incidents (no change), 1 research item (no change), 0 news items (no change), 0 policy items (no change).
Critical and high advisories
Vulnerability records rated critical or high, newest first.- Critical
CVE-2025-9556: Langchaingo server side template injection through prompt parsing
CVE-2025-9556NVD/CVE Database - Critical
CVE-2025-58434: Flowise forgot-password endpoint returns reset token enabling account takeover
CVE-2025-58434NVD/CVE Database - High
CVE-2025-6638: Hugging Face Transformers ReDoS in MarianTokenizer remove_language_code
CVE-2025-6638NVD/CVE Database - High
CVE-2025-55319: Ai command injection in Agentic AI and Visual Studio Code over network
CVE-2025-55319NVD/CVE Database - Critical
CVE-2025-59041: Claude Code code execution via malicious git user email before workspace trust
CVE-2025-59041NVD/CVE Database - Critical
CVE-2025-58764: Claude Code confirmation prompt bypass through command parsing error
CVE-2025-58764NVD/CVE Database - High
CVE-2025-58756: MONAI insecure checkpoint loading enables deserialization code execution
CVE-2025-58756NVD/CVE Database
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.| Advisory | Exploitation | EPSS | Published |
|---|---|---|---|
| CVE-2025-58434: Flowise forgot-password endpoint returns reset token enabling account takeover CVE-2025-58434NVD/CVE Database | Not listed | 49.9% |
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 |
|---|---|---|---|---|
| jupyter-server-mcp | PyPI | FastMCP | 0.1.0 |
Topics that moved
Largest increases over the mean of the 4 previous weeks, for topics with at least 3 records in the week.| Topic | Records | Weekly mean, previous 4 | Difference |
|---|---|---|---|
| AI agents | 3 | 2.0 | +1.0 |
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.