Advisories for AI coding assistants, agents, MCP servers and AI platforms: prompt injection, leaked keys and poisoned tools.
Nine AI developer platforms disclosed breaches in October 2026. Stolen keys from stored secrets drove about 2.5M Bedrock calls. Revoke, then rotate.
Attackers with stolen gh CLI tokens shipped malware as LiteLLM 1.107.0 on PyPI, Docker Hub and GHCR. Check before running Python, then rebuild and rotate.
Prompt injection in GitHub issues let attackers reach CI secrets through Claude Code, Gemini CLI and Codex. Upgrade, and keep untrusted input away from secrets.
Poisoned Trivy and KICS actions and images, LiteLLM 1.82.7/1.82.8 and Telnyx 4.87.1/4.87.2 stole CI and developer secrets. Check, then rotate.
