AI Coding Live News

Wiz "Black October" report: at least nine AI developer platforms breached in October, with stolen API keys feeding an LLMjacking resale market

Cloud security firm Wiz published research on October 30 saying at least nine AI developer platforms disclosed incidents this month: Fireworks AI, Andromeda, Zeabur, Lightning AI, OpenCode, Railway, Warp, CommandCode and Northflank. Attackers hunted stored environment variables, especially keys for paid AI models; Wiz traced two stolen enterprise keys to roughly 800,000 and 1.7 million Amazon Bedrock calls, which it estimates likely ran over $100k at list price in those two cases alone.

Wiz "Black October" report: at least nine AI developer platforms breached in October, with stolen API keys feeding an LLMjacking resale market

Key Takeaways

  • Scale: between October 6 and 30, at least nine AI developer platforms disclosed incidents, and Zeabur is shutting down as a result (Wiz blog)
  • Methods: Fireworks, OpenCode and Warp reported signs of an "agent swarm" attack, and OpenCode and CommandCode attributed theirs to "distillation" attempts; the common thread is hunting stored environment variables that grant AI access
  • Case A: one stolen key drove about 800k Bedrock calls over 30 hours, about 90% successful, with Opus models making up three quarters (Wiz figures)
  • Case B: a single address made about 1.7 million calls in 13 hours, over a million successful; the two cases together likely exceeded $100k at list price
  • Resale chain: Wiz identified two sites selling discounted frontier-model access and saw both test the stolen keys
Read full story

LiteLLM Gateway Compromised in v1.107.0 Supply-Chain Attack: Emergency Rollback to 1.106.2 and Credential Rotation Issued

LiteLLM, a widely deployed unified proxy gateway powering millions of LLM and autonomous agent pipelines worldwide (including LangChain and OpenHands), suffered a critical supply-chain compromise. Attackers breached its automated CI/CD release pipeline, pushing a poisoned v1.107.0 release to PyPI and Docker Hub tags ('latest' and 'main-stable') equipped with a credential-harvesting payload targeting system environment variables and cloud API keys. Coordinated with security firms including SlowMist, the maintainers quickly contained the incident, yanked v1.107.0, restored PyPI to 1.106.2, and urged all operators to pin dependency versions and rotate API credentials immediately.

LiteLLM Gateway Compromised in v1.107.0 Supply-Chain Attack: Emergency Rollback to 1.106.2 and Credential Rotation Issued

Key Takeaways

  • LiteLLM release pipeline compromised, publishing trojanized v1.107.0 packages across PyPI and Docker Hub tags
  • Payload secretly exfiltrated host environment variables, harvesting model API keys, database credentials, and cloud secrets
  • Maintainers yanked the malicious package within hours, rolling PyPI and official Docker containers back to stable 1.106.2
  • Urges all agent and LLM platform operators to verify pinned package versions and execute immediate credential rotation
Read full story

Voyager launches: a desktop agent harness that drives Blender, DaVinci Resolve, After Effects and Ableton — 'the Codex for creative work'

Nullframe (the Moda team, YC F26) shipped Voyager, a local desktop agent harness that drives creative apps through their own scripting APIs, ships free Design/Video/DAW engines, and works with your own Claude/Codex sign-in or API keys. The launch post passed 1.48M impressions.

Voyager launches: a desktop agent harness that drives Blender, DaVinci Resolve, After Effects and Ableton — 'the Codex for creative work'

Key Takeaways

  • Launch post: ~1.48M impressions, 3,074 bookmarks, 2,457 likes on X
  • Drives Photoshop, Illustrator, After Effects, Premiere Pro, DaVinci Resolve, Final Cut Pro, Blender, Unity and Ableton Live; skills also cover Cinema 4D, Houdini, Remotion, Manim
  • ~40 built-in skills, MCP server support, and reuse of skills installed for Claude Code / Codex / Cursor
  • Free app with BYO agent/keys; paid plans from $19/mo, generation billed at provider cost with no markup
  • Apple Silicon + macOS 15 required; Windows 11 / Linux in alpha; desktop v0.1.84 shipped Oct 8
Read full story
Linked Models & Agents:

Clampdown open-sources a hardened container sandbox for Claude Code, Codex, and more

@DanKornas highlighted Clampdown (github.com/89luca89/clampdown), a hardened container sandbox for coding agents: Landlock filesystem rules before the binary starts, deny-by-default egress with an allowlist, real API keys held in a separate auth proxy while the agent gets a dummy key, OCI hooks for nested containers, plus launch helpers for Claude Code, Codex, OpenCode, and pi (GPL-3.0-only).

Key Takeaways

  • Landlock filesystem rules bind the agent to the project directory before start.
  • Real keys stay in an auth proxy; the agent gets a dummy key and deny-by-default egress.
  • Launch helpers for Claude Code, Codex, OpenCode, and pi; GPL-3.0-only.
Read full story
ADSponsored

open-usage: open-source terminal dashboard for Claude Code, Codex, and OpenCode Go usage

Arion (@refatul_arion) open-sourced open-usage: a fast terminal dashboard with no account or API keys that shows Claude Code, Codex, and OpenCode Go usage in one place (npx open-usage).

Key Takeaways

  • Open-source CLI: run with npx open-usage.
  • Coverage: Claude Code, Codex, and OpenCode Go usage in one view.
  • Privacy: no account or API keys required.
Read full story

Pi v0.85.1: GPT-6 Astra via OpenAI API keys and Codex; fixes 0.85.0 SDK import break

Pi Changelog ships v0.85.1: GPT-6 Astra is available via OpenAI API keys and OpenAI Codex subscriptions, and SDK import failures from 0.85.0 accidentally published experimental code are fixed. Experimental/plugin subpaths and server/client commands are now source-only via pi-test.sh; local SDK and stdio RPC API stay unchanged.

Key Takeaways

  • v0.85.1 unlocks GPT-6 Astra via OpenAI API keys and Codex subscriptions.
  • Fixes SDK import failures from 0.85.0 accidental experimental publish.
  • Experimental/plugin subpaths are source-only via pi-test.sh; local SDK and stdio RPC unchanged.
Read full story

Grok Bot can buy on the web via Stripe Link with per-purchase single-use cards

Grok Bot can now complete purchases on the internet. Users connect Stripe Link, send a bot shopping, and approve each spend request; the bot then receives a secure, single-use card for that payment. The feature is currently available to users in the United States, with mobile rollout next. Combined with Elon Musk's follow-up that Grok Bot will not only purchase but also find and negotiate the best deal, the product is moving from research-and-code agent toward an economic actor with a wallet. For developers, the interesting primitive is not the demo checkout, it is the approval-gated, single-use card model: spend is an explicit tool call rather than a stored card on an unbounded session. That design is closer to how coding agents should handle cloud spend, API keys, and SaaS seats. It also raises product and compliance questions about refunds, merchant disputes, and what happens when an agent follows a phishing checkout.

Key Takeaways

  • Grok Bot completes web purchases through Stripe Link after per-spend user approval and a single-use card.
  • The feature is live for US users, with mobile rolling out next.
  • Musk says the bot will also find and negotiate deals, turning the agent into a gated wallet.
Read full story
Linked Models & Agents: