Apple · October 2, 2026

Audit macOS Full Disk Access before giving an agent desktop authority

Why it matters

Apple’s October 2 notice explains that Full Disk Access bypasses privacy protections to support functions such as backup, but can also expose files, mail, messages and browsing history to broadly privileged applications. That exposure includes information belonging to other people in a user’s conversations. Apple says additional explicit grant controls are planned; the notice supplies no shipping date. For agent deployments, the immediate control is the permission already granted to the host application, not an assumption that a future operating-system change will constrain it.

My takeaway: Review System Settings → Privacy & Security → Full Disk Access and remove grants that the agent’s task does not require. Test the workflow with narrower access and inspect which application actually holds the permission before expanding its authority.
Keep exploring

More curated notes connected through Agent Security and AI Engineering.

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.

Microsoft Security Blog · guide

AI vulnerability research: measure reproducible findings and completed fixes

Microsoft’s FORGE account describes the work between a model’s vulnerability claim and a useful repair: reusable builds, duplicate removal, reachability checks, project-specific verification, reproducible triggers and regression tests. Structured rejection reasons help improve later searches. The useful operational measure is the flow of findings that survive verification and reach a fix, rather than the number of candidates generated. Reported successful-case costs exclude parts of screening, failed attempts and human work, so they are not the total cost of operating this pipeline.

OpenAI News · framework

Frontier training safety cases: connect evidence to enforced pause and rollback controls

OpenAI proposes training-run safety cases combining alignment evaluations, containment and monitoring with explicit operational ownership. Concrete measures include immutable transcripts, held-out incident tests, checks for evaluation gaming, response deadlines and fail-closed monitoring. Independent internal challenge, leadership vetoes and tracking downstream uses support stopping a run and reversing affected work. The article describes recommendations still being implemented, rather than audited proof that every safeguard already operates or that residual risk has been eliminated.