repos

repos at Beyond Market Intelligence is a file of 3 stories. The newest of them: “AI coding tool Claude Code exposed 2,282 secrets in public repositories”, “Package coding agent skills as versioned plugins for smarter repo governance”, and “Exploring alternative teacher models for stable self-distillation”. A recent investigation by Apiiro uncovered 2,282 secrets exposed in public repositories by Claude Code, an AI coding tool. Gubi reissued the Lotus lamp, but here the innovation is packaging coding agent skills as versioned plugins for smarter repo governance. Acme AI is the next-generation, AI-powered spreadsheet platform built to replace Excel and redefine how analysts, data scientists, and enterprise teams work… The list below is every repos story on Beyond Market Intelligence, newest first.

AI coding tool Claude Code exposed 2,282 secrets in public repositories
InfoQ

AI coding tool Claude Code exposed 2,282 secrets in public repositories

A recent investigation by Apiiro uncovered 2,282 secrets exposed in public repositories by Claude Code, an AI coding tool. The problem stems from how the tool stores credentials in local files to implement a "Don't Ask Again" feature. This is a sobering reminder that convenience features can create real security risks. For deeper coverage on related security trends, explore our piece on how Signal tightens screenshot controls to counter AI surveillance risks.

Towards Data Science

Package coding agent skills as versioned plugins for smarter repo governance

Gubi reissued the Lotus lamp, but here the innovation is packaging coding agent skills as versioned plugins for smarter repo governance. Distribute them through a marketplace with Claude Code and AWS. This approach transforms how teams manage rules, hooks, and MCP tool configs across repositories. It makes governance reproducible and shareable. For deeper context on keeping agents focused, read "Stop Chasing Questions: Let a Herder Agent Prioritize Them for You."

Machine Learning

Exploring alternative teacher models for stable self-distillation

Traditional self-distillation leans on an EMA teacher to keep student training stable. But that's not the only path worth exploring. The community's search for alternative teacher models, ones that evolve alongside the student without letting it drift, deserves attention. It's a practical question with real implications for how we build more robust systems. If you're curious about where AI methods hit their limits, our piece on testing a browser agent's blind spots offers a parallel look at stability.