The Coalition for Secure AI, an OASIS Open Project, published three principles for agentic systems. The principles call for agents that are human-governed and accountable, bounded and resilient with strict, purpose-specific entitlements, and transparent and verifiable through secure AI supply chain controls and telemetry that supports monitoring and forensics.
Why it matters
It is an industry consensus statement that bounded entitlements and forensic telemetry are baseline requirements for agents.
Key facts
As stated in the sources, with where to find them.
- Three principles: human-governed and accountable; bounded and resilient (strict, purpose-specific entitlements); transparent and verifiable (secure AI supply chain controls and telemetry for monitoring and forensics).Principles section
Findings that cite this record
No tracked finding cites this record yet.
Key questions this bears on
- Can AI agents defend and oversee systems on their own?Not yet. Agents are weak on realistic defensive benchmarks and monitors can be evaded; assistants help analysts who stay in charge.
Sources
Related records
May 15, 2026
Jan 31, 2025
Jun 3, 2026
May 6, 2026
May 1, 2026
Jan 8, 2026