The OWASP Agentic Security Initiative's threat taxonomy for agentic AI (memory poisoning, tool misuse, privilege compromise, resource overload, cascading hallucination, intent breaking, misaligned and deceptive behaviour, repudiation and untraceability, identity spoofing, overwhelming human-in-the-loop) maps cleanly onto seven specific enterprise controls: scoped non-human identity, action-class approval gates, decision audit logging at Article 12 evidence quality, MTTD-for-Agents layered detection, deployment-tier resource quotas, behavioural drift monitoring, and HITL throughput limits. An enterprise that operates these seven controls covers all ten OWASP threat classes; an enterprise missing more than two of the controls has structural exposure to at least four of the threat classes.
OWASP Agentic AI Top 10 enterprise walkthrough. 90-day review cadence. Watches: (1) revisions to the OWASP Agentic Security Initiative threat catalogue (active project, version revisions expected through 2026), (2) new threat classes added to the catalogue (e.g., agent-communication poisoning in multi-agent systems is an emerging T11 candidate), (3) regulatory enforcement actions that establish case-law-equivalent guidance on which threat classes constitute negligence under the EU AI Act.
/holding/AM-043/Embed this claimiframe + oEmbed
The card auto-updates when the claim's status, last-reviewed date, or correction log changes. Embedders never need to refresh — the card is rendered live from the canonical record.
Email-me when AM-043's status, next review date, or correction log changes. One email per change. No newsletter subscription, no other mail.
The claim: The OWASP Agentic Security Initiative's threat taxonomy for agentic AI (memory poisoning, tool misuse, privilege compromise, resource overload, cascading hallucination, intent breaking, misaligned and deceptive behaviour, repudiation and untraceability, identity spoofing, overwhelming human-in-the-loop) maps cleanly onto seven specific enterprise controls: scoped non-human identity, action-class approval gates, decision audit logging at Article 12 evidence quality, MTTD-for-Agents layered detection, deployment-tier resource quotas, behavioural drift monitoring, and HITL throughput limits. An enterprise that operates these seven controls covers all ten OWASP threat classes; an enterprise missing more than two of the controls has structural exposure to at least four of the threat classes.
About this register
The Reporting register tracks claims published from articles addressed to senior enterprise IT leaders — CIOs, IT directors, heads of platform. Claims are reviewed on a 30–90 day cadence; each review either reaffirms the claim, marks one substantive part as Partial, or marks it Not holding once the underlying evidence has been overtaken.
Recent corrections in Reporting
- AM-132 · Partial · 10 Jun 2026
One of four legs unanchored on re-review. The claim text attributes '12% of deployments clearing 300%+ ROI with 88% at or below break-even at 12-18 months' to the Stanford DEL 2026 Enterprise AI Playbook. Full-text verification on 10 Jun 2026 found no such figure in that source: the playbook (Pereira, Graylin, Brynjolfsson, Apr 2026) studies 51 successful deployments by design and contains no ROI distribution, no 300%-plus cohort, and no break-even measurement point (full finding at AM-029, correction of 10 Jun 2026). The only verified figure carrying the same 12/88 numerals is IDC research with Lenovo (via CIO.com, Mar 2025): roughly 88% of AI proof-of-concepts never reach production and roughly 12% graduate — a pilot-to-production graduation metric, not an ROI distribution. The Gartner 28%, McKinsey 23%/17%, and MIT NANDA 95% legs verify; they support a small high-performing tail and a large struggling body, but none documents the two-peak bimodal shape the claim asserts. Status Up -> Partial.
- AM-129 · Partial · 10 Jun 2026
One of three read-against anchors unanchored on re-review. The claim text cites 'Stanford Digital Economy Lab Enterprise AI Playbook (12/88 bimodal ROI distribution at 12-18 months)' and frames the realistic ROI band around 'the highest-discipline 12% cohort'. Full-text verification on 10 Jun 2026 found the playbook contains no 12/88 distribution, no bimodal ROI shape, and no 12-18-month ROI measurement point (full finding at AM-029, correction of 10 Jun 2026). The claim's core negative finding — no mid-market enterprise has produced a documented +240% ROI in 90 days under audited conditions — is unaffected; the McKinsey State of AI 2025 and MIT NANDA legs verify and continue to support it. The '12% cohort' framing has no verifiable referent. The only verified figure carrying the 12/88 numerals is IDC's pilot-graduation finding (roughly 88% of AI proof-of-concepts never reach production; via CIO.com, Mar 2025), a different metric. Status Up -> Partial.
- AM-201 · Partial · 10 Jun 2026
One of four named datasets unanchored on review. The claim text names 'Stanford DEL's 12% clearing 300%+ ROI vs 88% at or below break-even' as one of four independent datasets. Full-text verification on 10 Jun 2026 found the Stanford DEL Enterprise AI Playbook contains no such distribution — it studies 51 successful deployments by design and carries no ROI-realisation failure data (full finding at AM-029, correction of 10 Jun 2026). The McKinsey (23% scaling, 17% EBIT-attribution), Gartner (28% fully paying off), and MIT NANDA (95% no measurable P&L impact) datasets verify; the claim's spine stands on three datasets rather than four. The only verified figure carrying the 12/88 numerals is IDC's pilot-graduation finding (roughly 88% of AI proof-of-concepts never reach production; via CIO.com, Mar 2025), a different metric from an ROI distribution. Status Up -> Partial.
Reviews coming up in Reporting
- AM-063 · Holding · next +15d (27 Jun 2026)
AI agents executing financial transactions need a four-control bundle (action-approval gates by blast radius, kill-swit…
- AM-061 · Holding · next +15d (27 Jun 2026)
Production agentic-AI costs at scale routinely run multiples of POC projections, and a layered optimisation programme c…
- AM-003 · Partial · next +15d (27 Jun 2026)
GPT-5 Pro's tiered-subscription model forces enterprises to classify problems by computational difficulty — $200/month…