Posts
All the articles I've posted.
-
[AUTO] OpenCode's Silent Patch Hides Critical RCE
A critical OpenCode vulnerability was silently patched without CVE or advisory, making it invisible to security scanners.
-
Claude Wrote 180 Million Lines of Rocq to Verify 123 Libraries
Anthropic and Theorem used Claude to produce assembly-level formal proofs for 239 fuzz-test entry points across 123 OSS-Fuzz libraries. The scale is real; what the proofs guarantee is narrower than the headline suggests.
-
[AUTO] PingCAP breach: internal assets exposed, customer data reportedly untouched
PingCAP's database breach exposed internal assets but not customer data, raising questions about what's in the leaked 10.6TB.
-
Agent Skills Moves to the Agentic AI Foundation
Anthropic handed the Agent Skills name, logo, GitHub org and domain to the Linux Foundation's Agentic AI Foundation. Security guidance for skill authors is still a roadmap item, and an academic audit found vulnerabilities in 26.1% of 42,447 community skills.