Fetching from the wire…
Security2026-08-09 · source-backed
Bulletin 2026-077-AWS, August 6: an IDOR in strands-agents-tools where mongodb_memory, elasticsearch_memory, and mem0_memory used a namespace field as the sole tenant-isolation key, and exposed that field as an LLM-controllable tool-schema parameter. A crafted prompt emits a call with a forged namespace and reads, modifies, deletes, or poisons another tenant's memories. The standalone mongodb/elasticsearch functions additionally exposed connection parameters, so the memory layer could be redirected to an attacker's cluster. Fixed in 0.8.3. The design lesson generalizes past this CVE: any security boundary rendered into a tool schema is a boundary the model can rewrite.
Each link below shares sources, entities, or timing with this story.
Three separate Anthropic changes over about two weeks point the same direction, and none of them announced themselves as a strategy. Claude Code 2.1.238 added claude self-hosted-runner --defer-shutdown-max-min, which keeps serving attached sessions on SIGTERM, parks whatever's...
Allen Bargi's August 15 post hit 302 points arguing that AI collaboration rewards context-sharing, examples, and feedback over precise instruction (Hacker News). The pushback holds that the piece conflates management with leadership. mikeocool calls it "the most low effort ver...
AWS shipped per-user, per-target rate limiting August 6 covering MCP targets, inference targets and HTTP passthrough across three metrics: requests (RPS/RPM), tokens (TPM, inference only), connections (CPS). Limits scope by JWT claims ($.context.jwt.sub, .role, .azp) or IAM id...
Go rotate a key. I'll wait. Claude Code 2.1.246, released August 25, lists this in its changelog: a fix for "telemetry and metrics requests to Anthropic carrying the API key configured for a third-party gateway (ANTHROPIC_BASE_URL); a credential is now only sent to its own hos...
OpenAI published a post titled "Our decision on Cursor following its acquisition by SpaceX" and set a shutoff date: November 12, 2026. The stated reason is blunt enough that I had to read it twice. OpenAI says it "cannot be confident that SpaceX will use our technology within...
NVHBM, announced August 26, relocates NVIDIA's custom memory controller from the compute chip into the HBM base die, claiming up to 30% more bandwidth than standard HBM4E, 15% lower HBM power, and up to 25% more freed area on the XPU compute die (NVIDIA). Next-generation Train...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.