Raw vector
CVSS:4.0/AV:N/AC:H/AT:N/PR:N/UI:N/VC:N/VI:H/VA:N/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:XSummary
CVE-2026-57495 is a high-severity Missing Authentication for Critical Function (CWE-306) vulnerability. Its CVSS base score is 8.2 (High).
Operationally, exploitation aligns with the MITRE ATT&CK technique Exploit Public-Facing Application (T1190); ranked at the 20th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog.
This vulnerability is AI-related — categorised as AI Agent Protocols and Integrations; in the LLM/Generative AI Risks risk domain.
OWASP Top 10 for Web (2025)
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2026-46124
Vulnerability Data
AgenticMail gives AI agents real email addresses and phone numbers. In @agenticmail/claudecode prior to version 0.2.39, @agenticmail/codex prior to version 0.1.33, @agenticmail/core prior to version 0.9.43, and @agenticmail/openclaw prior to version 0.5.71, two inbound-mail handlers act on a privileged effect…
more
without verifying that the sender is the operator, while a sibling handler in the same repo does. The higher-impact one: any external email routed to the bridge inbox causes the dispatcher to resume the operator's Claude Code session with `permissionMode: 'bypassPermissions'`, embedding the attacker-controlled `from`/`subject`/`preview` verbatim into the prompt the resumed agent reads — an indirect prompt injection into a fully-privileged agent (Bash/Write/Edit/WebFetch + the agenticmail MCP toolbelt) running as the operator's OAuth identity. The sibling operator-query email-reply hook gates the same untrusted-From provenance with `isOperatorReplySender(replyFrom, config.operatorEmail)` (fail-closed); the bridge-wake path — a strictly higher-privilege effect — has no equivalent. @agenticmail/claudecode 0.2.39, @agenticmail/codex 0.1.33, @agenticmail/core 0.9.43, and @agenticmail/openclaw 0.5.71 contain a fix.
- CWE(s)
AI Security AnalysisAI
- AI Category
- AI Agent Protocols and Integrations
- Risk Domain
- LLM/Generative AI Risks
- OWASP Top 10 for LLMs 2025
- None mapped
- AI-specific weaknesses CR
- CWE-1427 — Untrusted email fields injected into privileged agent prompt without sender validation.
Mapped by Cyber Resilience · not in NVD. Poisoning and extraction cases are routed to MITRE ATLAS instead of a synthetic CWE.- Classification Reason
- Matched keywords: ai, claude, prompt injection, mcp
Related Threats
MITRE ATT&CK Enterprise TechniquesAI
Why these techniques?
Missing sender auth (CWE-306) on privileged email-triggered handler directly enables external email to trigger privileged agent execution via prompt injection.
CVEs Like This One
Affected Assets
Mitigating Controls
Control response
—
—
- 6 hardening rules · 3 OS baselines
V6.2.3V6.4.4V10.4.16V12.1.3
Likely Mitigating Controls AI
Per-CVE control mapping for this CVE has not run yet; the list below is derived from the weakness types (CWEs) cited in the NVD entry.
Requires established identification and authentication to unlock, mitigating missing authentication for continued system access.
Requiring identification and rationale for actions allowed without authentication ensures critical functions are not left unprotected by forcing review of authentication requirements.
Authorizing mobile device connections to organizational systems ensures authentication is performed for this critical access function.
Guarantees critical functions are protected by mandatory invocation of the access control mechanism.
Auditing sessions makes it possible to detect access to critical functions without required authentication.
The assessment process confirms authentication is present and effective for critical functions, preventing exploitation from missing authentication.
Certification assesses that critical functions have required authentication controls in place.
Disabling non-essential functions and services eliminates the need to secure them, reducing exposure from missing authentication on unnecessary components.
Mitigating Controls (NIST CSF 2.0) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.
Directly requires authentication of users/services/hardware, which eliminates missing authentication for critical functions.
Managing identities and credentials is a prerequisite for authentication but does not itself enforce it on critical functions.
Defining and enforcing authorizations assumes prior authentication and therefore only partially mitigates the absence of authentication.
Protecting networks from unauthorized access can be undermined by missing authentication but does not address the root authentication gap.
Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.
The control explicitly calls for authentication before any critical function is reached, eliminating the possibility of bypassing authentication for high-value operations.
Mandating authentication requirements for critical functions at the requirements-gathering stage ensures that essential operations are not left unprotected by missing login or verification mechanisms.
Mandating authentication for network services and critical functions stops attackers from invoking sensitive operations without credentials, closing gaps where authentication is absent for important capabilities.
Security engineering principles insist on authentication and authorization for every critical function, eliminating entry points that lack any access control mechanism.
Requiring strong authentication and access-privilege enablement for remote connections ensures that critical functions cannot be invoked without proper verification, closing a gap that would otherwise allow unauthenticated use.
Mandatory use of access cards, biometrics, or two-factor authentication ensures that critical physical areas cannot be entered without proper authentication.