What changed in AI security, Jul 7 to Jul 13, 2025
Jul 7 to Jul 13, 2025 (ISO week 2025-W28). Weeks run Monday to Sunday in UTC.
14 records published, +7 on the previous week: 12 vulnerabilities (+7), 0 incidents (no change), 1 research item (no change), 1 news item (no change), 0 policy items (no change).
Critical and high advisories
Vulnerability records rated critical or high, newest first.- High
CVE-2025-53536: Roo Code code execution via auto-approved Write to VS Code settings
CVE-2025-53536NVD/CVE Database - High
GHSA-2rhq-96q8-4vjq: LlamaIndex vulnerable to Path Traversal attack through its encode_image function
CVE-2025-6209GitHub Advisory Database - High
CVE-2025-3262: huggingface/transformers ReDoS in SETTING_RE regex in chat.py
CVE-2025-3262NVD/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.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.No tracked package published its first release with an LLM SDK, agent framework or MCP dependency in this week.
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.