What changed in AI security, Sep 1 to Sep 7, 2025
Sep 1 to Sep 7, 2025 (ISO week 2025-W36). Weeks run Monday to Sunday in UTC.
11 records published, -2 on the previous week: 10 vulnerabilities (+8), 0 incidents (no change), 1 research item (-2), 0 news items (-8), 0 policy items (no change).
Critical and high advisories
Vulnerability records rated critical or high, newest first.- High
CVE-2025-58374: Roo Code arbitrary code execution through npm install auto-approval
CVE-2025-58374NVD/CVE Database - High
CVE-2025-58372: Roo Code arbitrary code execution via unprotected .code-workspace files
CVE-2025-58372NVD/CVE Database - Critical
CVE-2025-58371: Roo Code GitHub workflow code execution via unsanitized pull request metadata
CVE-2025-58371NVD/CVE Database - High
CVE-2025-58370: Roo Code command parsing flaw allows arbitrary command execution via prompts
CVE-2025-58370NVD/CVE Database - High
CVE-2025-6984: langchain EverNoteLoader XML external entity injection in XML parsing
CVE-2025-6984NVD/CVE Database - Critical
CVE-2025-58357: 5ire content injection through chat page script gadgets
CVE-2025-58357NVD/CVE Database - High
CVE-2025-9959: smolagents Local Python execution sandbox escape via dunder attributes
CVE-2025-9959NVD/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.| Package | Ecosystem | LLM SDKs | Release | Released |
|---|---|---|---|---|
| inspect-scout | PyPI | Anthropic SDK, Google Gemini SDK, Hugging Face Hub / Transformers, OpenAI SDK | 0.1.0 | |
| bedrock-agentcore | PyPI | LangChain, LangGraph, Model Context Protocol SDK, Strands Agents | 0.1.3 | |
| google-adk-community | PyPI | Google Agent Development Kit | 0.0.1 |
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 | 5 | 1.3 | +3.8 |
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.