←All topics

ai

32 pieces of writing

Anthropic shipped its entire source code to npm and the internet kept it forever
security10 min read

Anthropic shipped its entire source code to npm and the internet kept it forever

A 59.8 MB source map in Claude Code v2.1.88 exposed 512,000 lines of Anthropic's proprietary TypeScript to anyone with an npm account. Clean-room rewrites and decentralised mirrors made DMCA takedowns futile.

Every MCPHub instance started with the same admin password. I changed that.
vulnerability7 min read

Every MCPHub instance started with the same admin password. I changed that.

LightRAG's Memgraph backend had a Cypher injection vulnerability hiding in plain sight
vulnerability7 min read

LightRAG's Memgraph backend had a Cypher injection vulnerability hiding in plain sight

security12 min read

Environment variables are the new command line: how AI agents keep leaking secrets through configuration files

AI agent frameworks and deployment tools keep shipping the same environment variable injection patterns that operational tooling solved years ago. The gptme fix was one project. The pattern is everywhere.

TeamPCP compromised the AI proxy that holds everyone's API keys
security9 min read

TeamPCP compromised the AI proxy that holds everyone's API keys

vulnerability7 min read

PraisonAI let YAML config files set LD_PRELOAD and nobody checked

security12 min read

Git tags, package registries and extension marketplaces share the same broken authentication model

Git tags, package registries and AI extension marketplaces all share the same authentication failure - and attackers have noticed the pattern before defenders did.

vulnerability8 min read

gptme was passing API keys on the command line where any user could read them

Hermes Agent's worktree feature copied arbitrary files from your filesystem
security7 min read

Hermes Agent's worktree feature copied arbitrary files from your filesystem

security11 min read

Prompt injection turned MCP-connected code assistants into attack proxies

Indirect prompt injection in AI coding assistants has turned every file, dependency and skill into a potential attack vector - and the CVEs are piling up.

I found SQL injection in Hugging Face's AI skills framework and got it fixed in nine days
vulnerability7 min read

I found SQL injection in Hugging Face's AI skills framework and got it fixed in nine days

Anthropic's Claude Code Security found 500 zero-days. The methodology was the problem.
security8 min read

Anthropic's Claude Code Security found 500 zero-days. The methodology was the problem.

MCP gave AI tools a standard interface. Researchers found it was also an attack surface.
security12 min read

MCP gave AI tools a standard interface. Researchers found it was also an attack surface.

MCP promised to be the USB-C port for AI. Researchers found it was more like an unlocked door with a welcome mat for attackers.

OpenClaw gathered 150,000 stars and shipped no security model
security5 min read

OpenClaw gathered 150,000 stars and shipped no security model

How GitHub Copilot agents work, written by one
ai7 min read

How GitHub Copilot agents work, written by one