SecurityWeek AI Security · October 29, 2026

Quarry: test agent detections across ordered tool calls and complete traces

Why it matters

Cisco’s open-source Quarry compiles rules over messages, tool calls, results and event order, with optional model signals. Its examples detect a private-data read followed by external communication and include a reversed-order negative case. The alpha framework returns matching evidence; applications still own enforcement. Example model stubs are not production detectors.

My takeaway: Pin a reviewed version and start with local positive and benign fixtures. Preserve tool-call relationships and session history, test reordered and missing events, and verify how incomplete scans are handled. Keep rules and credentials outside agent control. Review false positives before connecting findings to blocking, and redact sensitive trace content in diagnostics.
Keep exploring

More curated notes connected through Agent Security and Prompt Injection.

OpenAI News · framework

Pacing model development in an era of cyber-critical capabilities

OpenAI says preliminary evidence that Astra may meet its Critical cybersecurity threshold led it to pause frontier reinforcement-learning work for two weeks and keep its largest planned run on hold. New safeguards include stronger workload and network isolation, continuous boundary testing, token-level monitoring that escalates suspicious tool activity, and broader alignment checks for deception, reward hacking, and unauthorized access.

OWASP GenAI Security Project · guide

OWASP Top 10 for Agentic Applications for 2026

OWASP's community guide organizes agentic-system risk into ten categories, including goal hijacking, tool misuse, identity and privilege abuse, memory poisoning, insecure inter-agent communication, cascading failures, and rogue-agent behavior. It provides a shared taxonomy and mitigation starting point rather than a certification checklist or evidence that a deployed system is secure.

OpenAI News · framework

A blueprint for democratic governance of frontier AI

OpenAI proposes a three-part U.S. frontier-AI governance model: harmonize emerging state safety laws into a federal baseline, strengthen CAISI as an evaluation and standards institution, and coordinate a broader resilience program. Proposed controls include severe-risk evaluations, transparency reports, independent audits, safety-incident reporting, model-weight security, whistleblower protection, and periodic technical assessments.