MITRE
A US federally funded, not-for-profit R&D organization that operates government-sponsored research centers; maintains CVE and ATT&CK and contributes engineering staff to IETF and NIST standards work.
In our briefings
The claim each of the newest briefings on MITRE would have you leave with.
The IETF datatracker shows that the IESG approved OAuth Identity and Authorization Chaining Across Domains (draft-ietf-oauth-identity-chaining) as a Proposed Standard on 22 June 2026, and that it has been in the RFC Editor's queue since that day. Revision 17, the text we read, was posted on 19 July 2026 during that editing. Its authors are Arndt Schwenkschuster and Pieter Kasselman of Defakto Security, Kelley Burgin of MITRE, Mike Jenkins of NSA-CCSS, Brian Campbell of Ping Identity and Aaron Parecki of Okta. Campbell co-wrote RFC 8693 and RFC 7523, the two RFCs the draft combines, and Parecki co-wrote RFC 9728, one of the ways it names for finding the other domain's authorization server. The working group's write-up for the IESG lists implementations, among them Keycloak 26.5 and Okta's. Two other drafts we have read point to it: the transaction-tokens draft leaves crossing domains to it, and the AI agent authentication draft says cross-domain access SHOULD use identity chaining.
OAuth's draft for crossing trust domains is approved for publication and never says agentBI-FIND-2026-0184
OWASP's AIVSS v0.8 starts from a CVSS v4.0 base score and adds an uplift worth part of the gap between that base and 10. Ten agentic factors, each scored 0, 0.5 or 1, set the share, and an exploit-maturity multiplier scales it, by default 0.97. With the default mitigation factor of 1.0 (no or weak mitigation), all ten worked examples in the document land between 7.1 and 10.0, seven Critical and three High, and a goal-manipulation flaw with a CVSS base of 2.1 comes out at 7.1. The authors read a jump like that as a sign that the agentic deployment context, not the technical flaw, is the main risk driver. On our reading of the formula, a score can only fall below its CVSS base through the mitigation factor, and the document warns that AIVSS scores are not directly comparable to CVSS base scores.
OWASP's AIVSS lifts a CVSS 2.1 agent flaw to 7.1, and all ten worked examples land High or CriticalBI-FIND-2026-2299
Corvic's design keeps API keys out of the model entirely: agent code is given only connector names, and a vault outside the agent's process attaches the credential to outbound calls for the host each connector declares. That removes the cheapest leaks, a key pasted into a prompt or echoed into a log, which Corvic's own scoring drops from 25 to 4 on a 25-point scale. It does much less against an agent that misuses a connector it legitimately holds: the over-privileged connector only falls from 20 to 15. The evidence is Corvic testing Corvic: 16 scripted probes in its own tenant, no language model under attack, no prompt-injection run, and ordinal scores the authors assigned. Redirects, a compromised destination and admin access were not tested.
Corvic's own tests find its agent vault keeps keys out of prompts but does much less against a misused connectorBI-FIND-2026-0690
Cited in 3 briefings
Every briefing that discusses this term, newest first.
- OAuth's draft for crossing trust domains is approved for publication and never says agent
Draft · · IETF OAuth Working Group · Arndt Schwenkschuster et al. · Jul 19, 2026
- OWASP's AIVSS lifts a CVSS 2.1 agent flaw to 7.1, and all ten worked examples land High or Critical
Article · · OWASP AIVSS project · Ken Huang et al. · Oct 22, 2026
- Corvic's own tests find its agent vault keeps keys out of prompts but does much less against a misused connector
Paper · · arXiv · Kenney, Corvic AI · Sep 27, 2026