AI safety & securitymedium
Prompt injection still drives most agentic AI security failures in production
Vulnerabilities mentioned
All| CVE | Vulnerability | CVSS | EPSS | Signals | Published |
|---|---|---|---|---|---|
| CVE-2025-59532 | Codex CLI: In versions 0.2.0 to 0.38.0, due to a bug in the sandbox configuration logic, Codex CLI could treat a model-generated cwd as the… | 8.6 | <1% | ||
| CVE-2025-6514 | Critical OS Command Injection in mcp-remote Enables RCE via Untrusted MCP Servers | 9.6 | 78% | ||
| CVE-2026-22708 | Cursor: Hen the Cursor Agent is running in Auto-Run Mode with Allowlist mode enabled, certain shell built-ins can still be executed… | 7.2 | <1% |
From the original article
4 min read at helpnetsecurity.com
A backdoor sat on PyPI for three hours in March 2026. Nearly 47,000 downloads occurred during the window. The compromised package, LiteLLM, serves as the language-model gateway for CrewAI, DSPy, Microsoft GraphRAG, and dozens of other AI agent frameworks.
By @helpnetsecurity · helpnetsecurity.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.