Review this: Amazon Q, Claude Code and MCP made repository text a…
Latest intel
View all →Trending on GitHub
· this weekFixes shipped
AI agents changed repository poisoning from a code-review problem into an execution problem because models now read untrusted project text, interpret obfuscated code and act through trusted developer tooling.
AI-assisted development tools changed the supply-chain boundary: repository text, hidden prompts and tool descriptions can now steer agents toward code execution, secret theft and data exfiltration.
Threat Feed
liveOpenClaw's 470 advisories show how cloud AI platforms turn prompt handling, tool calls and host execution into an unauthenticated RCE pattern at scale.
Authentication bypass keeps recurring because modern applications validate identity at convenient edges, then perform critical operations in layers that no longer know whether access was proven.
Supply chain compromise is shifting from static package poisoning towards runtime weaponisation, where trusted code becomes a credential harvester, traffic broker or covert infrastructure node after deployment.
More research
CIFSwitch CVE-2026-46243 and PraisonAI show why vertical movement often follows from designs that let low-trust identities shape high-trust operations.
Gogs, PraisonAI and KnowledgeDeliver show why authentication bypass in self-hosted platforms is often an architectural failure, not a missing if statement.
May 2026 supply-chain compromises showed that poisoned developer tooling now targets the identity and execution layer before code reaches a repository.
Supply chain compromise has shifted from stealing credentials to poisoning package ecosystems through compromised CI/CD systems, maintainer accounts and trusted execution paths.
Google Project Zero's Pixel 10 zero-click chain shows how Android hardening changes exploit shape without removing reachable attack surface in media parsing and device drivers.
Recent vm2, NodeVM and Ollama flaws show a recurring failure pattern: developer-friendly JavaScript isolation is being treated as a hard security boundary when the runtime was never designed to provide one.
Checkmarx KICS, npm Bitwarden CLI packages and GlassWorm show how supply chain compromise has moved from poisoned code to weaponised developer trust.
A compromised AI productivity tool called Context.ai gave attackers OAuth access to a Vercel employee's Google Workspace, pivoting into internal systems. The AI tool supply chain is the new CI/CD supply chain.
Eighteen months of supply chain attacks against AI infrastructure reveal a structural pattern: the build pipeline, the package registry and the runtime protocol all share the same trust model failure.
