Raw vector
CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:C/C:N/I:H/A:LSummary
CVE-2025-69220 is a high-severity Improper Access Control (CWE-284) vulnerability in Librechat Librechat. Its CVSS base score is 7.1 (High).
Operationally, exploitation aligns with the MITRE ATT&CK technique Exploit Public-Facing Application (T1190); ranked at the 22th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog; a public proof-of-concept is referenced.
This vulnerability is AI-related — categorised as LLM Application Platforms; in the LLM/Generative AI Risks risk domain.
The strongest mitigations our analysis identified map to AC-24 (Access Control Decisions) and AC-25 (Reference Monitor) — see the control section below for these in your framework.
Deeper analysis AI-assisted summary
Synthesised by an AI model from the NVD description and linked references — a reading aid, not an authoritative source.
CVE-2025-69220 is an improper access control vulnerability affecting LibreChat, an open-source ChatGPT clone with additional features, specifically in version 0.8.1-rc2. The flaw lies in the failure to enforce proper access controls for file uploads to an agent's file context and file search functionality, linked to CWE-284 (Improper Access Control) and CWE-862 (Missing Authorization). This allows unauthorized modifications to agent configurations through file uploads. The vulnerability carries a CVSS v3.1 base score of 7.1 (AV:N/AC:H/PR:L/UI:N/S:C/C:N/I:H/A:L), indicating high integrity impact with scope change.
An authenticated attacker with low privileges (PR:L) who has access to an agent ID can exploit this over the network (AV:N), though it requires high attack complexity (AC:H) and no user interaction (UI:N). By uploading malicious files to the file context or file search of arbitrary agents, the attacker can alter their behavior, even without explicit permissions for those agents. This leads to high integrity impact (I:H) and low availability impact (A:L), potentially enabling unauthorized control over AI agent operations in a scoped but changed environment (S:C).
The GitHub security advisory (GHSA-xcmf-rpmh-hg59) and release notes confirm the issue is fixed in LibreChat version 0.8.2-rc2, with the patching commit available at https://github.com/danny-avila/LibreChat/commit/4b9c6ab1cb9de626736de700c7981f38be08d237. Security practitioners should upgrade to the fixed release and review access to agent IDs in multi-user deployments.
OWASP Top 10 for Web (2025)
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2025-206261
Vulnerability Data
LibreChat is a ChatGPT clone with additional features. Version 0.8.1-rc2 does not enforce proper access control for file uploads to an agents file context and file search. An authenticated attacker with access to the agent ID can change the behavior…
more
of arbitrary agents by uploading new files to the file context or file search, even if they have no permissions for this agent. This issue is fixed in version 0.8.2-rc2.
- CWE(s)
AI Security AnalysisAI
- AI Category
- LLM Application Platforms
- Risk Domain
- LLM/Generative AI Risks
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- Matched keywords: chatgpt, librechat
Related Threats
MITRE ATT&CK Enterprise Techniques
CVEs Like This One
Affected Assets
Mitigating Controls
Control response
—
—
- 13 hardening rules · 4 OS baselines
V10.3.5
Mitigating Controls (NIST 800-53 r5) AI
Directly enforces approved authorizations for logical access, stopping unauthorized actors from reaching resources.
AC-24 mandates that access control decisions are applied to each request, preventing bypass of authorization logic.
AC-25 requires a tamperproof, always-invoked reference monitor that ensures authorization checks cannot be omitted.
Enforces flow-control policies that restrict information movement between subjects and objects.
Documents duties and assigns access so that no single account can bypass intended restrictions.
Limits each account to the minimum privileges needed, reducing the chance of unauthorized access.
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.
Explicitly requires defining, enforcing, and reviewing authorizations and least privilege, directly preventing missing authorization checks.
Hardened baselines and deviation monitoring directly eliminate most configuration-induced access-control defects, yet CWE-284 also encompasses code-level and design flaws outside the scope of configuration management alone.
Secure SDLC practices catch most access-control defects during design/coding/testing (mostly), yet leave residual risk from runtime configuration, architecture, and operational controls (partial).
PR.AA-01 supplies managed identities/credentials that support but do not implement access-control decisions, so it only partially prevents CWE-284 in either direction.
Authentication directly blocks unauthenticated actors (partial prevention of CWE-284) but leaves authorization logic, policy enforcement, and role checks untouched, so the control neither eliminates nor fully mitigates the broader weakness.
PR.DS-01 encryption mitigates impact of failed access checks on stored data but neither implements nor constrains access-control logic itself.
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.
Defining and enforcing explicit access rights and restrictions for each entity directly stops the assignment of permissions that exceed what is required, eliminating the root condition that allows improper access control.
Formal authorization, role-based provisioning, and timely revocation of access rights directly stop the creation of accounts or permissions that exceed what the business actually needs.
By enforcing explicit rules on which identities or groups may perform read, write, delete or execute operations and by denying anonymous access to sensitive data, the control directly stops the creation of overly permissive or missing access-control checks.
Requiring one-to-one mapping of identities to entities and timely removal of unused identities directly stops attackers from leveraging stale or shared accounts to bypass access restrictions.
By explicitly transferring security roles and responsibilities when personnel change jobs or leave, the control reduces the chance that former employees retain access rights they no longer need, thereby limiting improper access control.
Physical entry controls enforce explicit authorization and authentication at every access point, directly stopping unauthorized actors from reaching information-processing assets.
Hardening callouts derived
Configuration rules from DISA STIG baselines that bear on weaknesses of the type cited by this CVE. Each rule is shown with the relationship its mapping actually records, against the CWE it was authored against. Derived via CVE→CWE over `controls_xwalks` (authoritative rows only; rows rated `none` are excluded).
Oracle Linux 8 (4 rules)
- V-248581 OL 8 must require users to provide a password for privilege escalation. prevents CWE-862
- V-248597 There must be no "shosts.equiv" files on the OL 8 operating system. prevents CWE-284
- V-248598 There must be no ".shosts" files on the OL 8 operating system. prevents CWE-284
Oracle Linux 9 (2 rules)
- V-271758 OL 9 file systems must not contain .shosts files. prevents CWE-284
- V-271757 OL 9 file systems must not contain shosts.equiv files. prevents CWE-284
RHEL 7 (4 rules)
- V-251704 The Red Hat Enterprise Linux operating system must not be configured to bypass password requirements for privilege escalation. prevents CWE-862
- V-204429 The Red Hat Enterprise Linux operating system must be configured so that users must provide a password for privilege escalation. prevents CWE-862
- V-204606 The Red Hat Enterprise Linux operating system must not contain .shosts files. prevents CWE-284
RHEL 8 (2 rules)
- V-230283 There must be no shosts.equiv files on the RHEL 8 operating system. prevents CWE-284
- V-230284 There must be no .shosts files on the RHEL 8 operating system. prevents CWE-284