Space secrets security update

Security incident disclosure — July 2026

An update on our safety & security practices

An update on our safety & security practices

Hardware Keystores for AI Agent Signing Workflows: A Zero-Trust MCP Enforcement Architecture

arXiv:2608. 06130v1 Announce Type: cross Abstract: AI agents performing cryptographic operations (signing Git commits, authenticating API calls, issuing certificates) currently store private keys in software-accessible locations: plaintext files, environment variables, or container memory.

2024 Security Feature Highlights

When Agents Talk, Secrets Travel: Topology-Driven Leakage and Recipient-Conditioned Sanitization in Multi-Agent LLM Systems

arXiv:2610.16039v1 Announce Type: cross Abstract: Multi-agent LLM systems (MALS) introduce a privacy-leakage problem that conventional sensitivity-based defenses miss, since information disclosed to...

How Hugging Face Scaled Secrets Management for AI Infrastructure

StratFL: Countering Covert Model Poisoning Attacks with Strategic Federated Learning

The paper introduces StratFL, a strategy for federated learning that counters covert model poisoning attacks by modeling the interaction between the server and attacker as an imperfect repeated game. It proposes new belief‑update algorithms for both parties and an adversarial search method to detect and mitigate intermittent poisoned updates. Experiments on MNIST and CIFAR‑10 show that StratFL improves accuracy by about 10% over existing defenses while demonstrating convergence of the belief updates across various security scenarios.

STAR-FL: Secure Federated Learning with Spatial-Temporal Analysis and Robust Aggregation

arXiv:2608. 14861v1 Announce Type: cross Abstract: Data poisoning attacks pose serious security threats to Federated Learning (FL) systems in Computer Vision.

Privacy-Preserving AI Verification via Minimal Information Disclosure

arXiv:2608. 02774v1 Announce Type: cross Abstract: AI verification crosses a trust boundary: a verifier must learn enough to establish an authorized claim, yet the same evidence can reveal sensitive details about the model, workload, or hardware.

ShareLock: A Stealthy Multi-Tool Threshold Poisoning Attack Against MCP

arXiv:2606. 27027v1 Announce Type: cross Abstract: With the rapid evolution of LLM-driven agents, Model Context Protocol (MCP), an open protocol bridging LLMs with external tools, has quickly become foundational to modern agent ecosystems.

eMudhra Intermediate CA Compromise

The private keys of eight eMudhra intermediate CA certificates have been compromised, affecting root chains trusted by major browsers and many downstream trust stores. Software that bundles trusted certificates must update their lists, and Linux distributions are advised to refresh ca‑certificates packages. Updated Python tools (uv 0.13.4, pip 26.2.2, certifi 2026.10.19) now include the revised certificate lists.

Trusted access for the next era of cyber defense

OpenAI expands its Trusted Access for Cyber program, introducing GPT-5. 4-Cyber to vetted defenders and strengthening safeguards as AI cybersecurity capabilities advance.