Blast radius
blast-radius
The potential damage if an agent or component fails or is compromised.
In our briefings
The claim each of the newest briefings on Blast radius would have you leave with.
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
NatWest's complaints agent writes investigation summaries for complaint handlers and has been live since February. Around 14,000 of its cases were scored by both a human validator and an LLM judge. Osborne says the judge's faithfulness scores averaged 0.97 with very little spread, against a human mean of 0.83 with a much wider one. The average error of 0.2 might look acceptable, he says, "but the correlation is almost zero." Changing only the model behind the judge cut most of its margin over the pass threshold, which is why he says the judge model "becomes part of your configuration". NatWest moved the judge to a different model family from the agent, which he presents as the effective way to bring the two scores closer together.
NatWest found its LLM judge barely tracked human reviewers, and an 83% pass rate hid 43% on topic changesBI-FIND-2026-2060
Niyikiza's tokens let one AI agent narrow another's authority down to the values a tool's arguments may take. A root token from the authorization server maps tool names to constraints on each argument (exact, range, one_of, subset and five more core types), and a holder can derive a child offline with fewer tools or tighter constraints, sign it with its own key and pass it on. Argument matching stays closed by default in revision -02: the enforcement point refuses an argument the token does not name unless the issuer adds a "*" entry, which the draft says issuers should not use for tools with side effects. The enforcement point checks the whole chain with only the root issuer's trust anchor and no network call. If it skips or botches the narrowing check, it "provides no blast radius containment", in the draft's words.
Niyikiza's agent tokens narrow to a tool's arguments offline; revision -02 breaks -01 implementationsBI-FIND-2026-0532
›Cited in 16 briefings
Every briefing that discusses this term, newest first.
- 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
- NatWest found its LLM judge barely tracked human reviewers, and an 83% pass rate hid 43% on topic changes
Video · · AI Engineer · Uploaded November 4, 2026
- Niyikiza's agent tokens narrow to a tool's arguments offline; revision -02 breaks -01 implementations
Draft · · IETF Datatracker · Niki Aimable Niyikiza · Jun 15, 2026
- Unum found agents without owners; Honeywell warns about inherited developer access
Video · · SailPoint · Oct 16, 2026
- Entra can send risky user consent to an admin even when tenant policy would allow it
Podcast · · Entra.Chat · Stop the Bleeding: Cleaning Up Apps, Secrets and Consent in Microsoft Entra · Oct 17, 2026
- AAuth's bootstrap guide makes device attestation optional and lets a new key mean a new agent
Draft · · IETF Datatracker · Dick Hardt, Hellō · Sep 28, 2026
- A phishing agent hosted on Microsoft's own domain, and why giving agents identities does not stop it
Article · · WorkOS Blog · Maria Paktiti · Sep 29, 2026
- Opal's access-review AI runs with a person approving by default, and an Opal engineer still reads the rejections
Podcast · · Identity at the Center · #448 - Sponsor Spotlight - Opal Security · Sep 17, 2026
- A county CTO says identity is already critical infrastructure, and nobody will own it until someone declares it
Podcast · · Identity at the Center · #452 - When Identity Becomes Critical Infrastructure with Shea McGrew · Oct 5, 2026
- Okta's answer to agent sprawl: put the identity provider between every agent and every app
Podcast · · Cloud Security Podcast · Who Governs Your AI Agents? Identity, Offboarding & Open Standards · Jul 2, 2026
- Mission-Bound OAuth's author now says the mission object does not belong in OAuth
Article · · Control Plane by Karl McGuinness · Karl McGuinness · Mar 15, 2026
- SailPoint's product chief wants an agent's access checked before each tool call and again at each resource access
Podcast · · The Security Strategist · Who Owns an AI Agent? Rethinking Identity, Security, & Accountability · Aug 27, 2026
- WorkOS hands a personal AI agent a key its user owns, then contradicts itself on whether the key can be narrower
Article · · WorkOS Blog · Maria Paktiti · May 15, 2026
- Auth0's case for Token Vault: take the user ID out of the token call and let the session prove whose token it is
Article · · Auth0 Blog · Abhishek Hingnikar, Okta · Nov 4, 2025
- OWASP's multi-agent threat guide finds the hop where a user's permission check drops out, but names no fix
Article · · OWASP GenAI Security Project · OWASP Agentic Security Initiative · Apr 22, 2025
- TLS clients must match a service they chose independently of the certificate
Article · · RFC Editor · Peter Saint-Andre et al. · Nov 8, 2023