Category
security
3 posts in this category.
·7 min read
OpenAI agents and the RubyGems attack: what's confirmed
RubyGems confirms a May spam campaign and yanked malicious gems; researchers blame OpenAI agents; OpenAI hasn't verified it. Timeline, sources, vendor clause.
·13 min read
TypeScript AI Agent Observability and Tracing Modules
5 paste-ready TypeScript AI agent observability modules: trace context, cost metering, event logging, tool-call tracing, and OpenTelemetry export.
·14 min read
TypeScript AI Agent Security Incident Response Playbook
4 drop-in TypeScript files (64 to 118 lines) with a 20-test Vitest suite: an incident response playbook for prompt injection, runaway loops and tool calls.