CVE Intelligence
Critical Injection exploit reference

CVE-2026-25481 — Langroid code injection via TableChatAgent pandas_eval filter bypass (CWE-94)

Langroid is a framework for building large-language-model-powered applications. Prior to version 0.59.32, there is a bypass to the fix for CVE-2025-46724. TableChatAgent can call pandas_eval tool to evaluate the expression. There is a WAF in langroid/utils/pandas_utils.py introduced to block code injection CVE-2025-46724. However it can be bypassed due to _literal_ok() returning False instead of raising UnsafeCommandError on invalid input, combined with unrestricted access to dangerous dunder attributes (__init__, __globals__, __builtins__). This allows chaining whitelisted DataFrame methods to leak the eval builtin and execute arbitrary code. This issue has been patched in version 0.59.32.

Published Feb 4, 2026 · Updated Oct 13, 2026 · Sources: NIST National Vulnerability Database, CVE Program (cve.org) e CISA ADP · CNA: GitHub_M

Who exploits it and how urgent it is

A 0–100 score combining confirmed exploitation, ransomware and APT use, public exploits, EPSS and severity.

No exploitation signal in the sources consulted so far.
How the score was calculated
  • EPSS 0.8% (30-day exploitation probability)+8
  • Technical severity (critical)+10
  • CISA SSVC: exploitation "poc"+5
  • Automatable exploitation (SSVC)+3

The score orders the patch queue; it does not replace your asset context (internet exposure, criticality, compensating controls).

Triage

Is it exploited, how likely is exploitation, what does it touch, and how severe do the sources call it.

Exploitation
Not confirmed
Not in CISA KEV — an absence of record, not proof it is unexploited.
EPSS FIRST
0.82%
ahead of 56% of scored CVEs · Oct 14, 2026
Affects
Langroid
Langroid
CVSS base
9.6
Critical · 3 source(s)

CISA SSVC assessment CISA

Three decision points CISA publishes for the CVEs it assesses (SSVC 2.0.3). A stakeholder decision, not a severity score.

Exploitation
Proof of concept
none · proof-of-concept · active
Automatable
Yes
can an attacker script the kill-chain steps
Technical impact
Total
partial · total control of the vulnerable component

Remediation

Fixes and mitigations documented by the sources — linked to the original advisory.

  • Documented patch — github.com (NIST National Vulnerability Database)

First 24 hours

Ordered from the record’s own fields — exposure first, because you cannot patch what you have not found. A rule-generated starting point.

  1. Identify exposed assets running the affected vendor/product/version combinations (Langroid Langroid).
  2. The attack is network-based and needs no privileges: restrict exposure (ACLs, VPN, WAF) until patched.
  3. Apply the fixed version or the patch documented under Remediation.
  4. Exploitation requires user interaction: tighten email/web filtering and warn affected users.
  5. Search available logs for exploit probes matching the vulnerability class (injection), errors and authentication anomalies.

Affected scope

Vendor, product and versions as the sources word them.

VendorProductVersionsStatusSource
Langroid Langroid < 0.59.32 Vulnerable NIST National Vulnerability Database
Langroid Langroid version < 0.59.32 Vulnerable CVE Program (cve.org) e CISA ADP

Attack characteristics

The CVSS vector, decoded. It describes the attack, not your exposure to it.

Attack vector
Network
Attack complexity
Low
Privileges required
None
User interaction
Required
Scope
Changed
Confidentiality
High
Integrity
High
Availability
High

Every base score collected

Sources score independently and may disagree; each row says who scored it and under which version.

ScoreVersionSeverityExpl.ImpactScored by
9.4 CVSS 4.0 Critical — — security-advisories@github.com via NIST National Vulnerability Database
9.4 CVSS 4.0 Critical — — GitHub_M via CVE Program (cve.org) e CISA ADP
9.6 CVSS 3.1 Critical 2.8 6.0 nvd@nist.gov via NIST National Vulnerability Database
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H (score shown at the top: nvd@nist.gov)

Weakness MITRE

Weakness class according to MITRE’s CWE catalog.

CWE-94 · Code Injection

Other CVEs with this weakness →

EPSS over time FIRST

Oct 13, 2026 → Oct 14, 2026 · 2 reading(s) · max 0.82%

Detection

Read off the CVSS vector and the weakness class. Starting points, not tested rules.

  • Prioritize edge telemetry for the network-reachable component (proxy, WAF, IDS/IPS).
  • Look for parameters with command/query metacharacters and unexpected child processes of the service.
web/proxy/WAF logsnetwork IDS/IPSapplication logsendpoint telemetry (EDR)

Analysis and videos

CVE-2026-25481: Langroid code injection via TableChatAgent pandas_eval filter bypass (CWE-94)
Langroid versions before 0.59.32 contain a bypass of an earlier fix (CVE-2025-46724) for code injection in the pandas_eval tool used by TableChatAgent. NVD rates the issue CVSS 3.1 9.6 (critical), and the upstream patch is in version 0.59.32. No confirmed exploitation appears in the sources consulted and the CVE is not listed in CISA KEV.

Timeline

What happened to this CVE, newest first.

  • 2026
  • Affected products added · langroid/langroid
    Oct 13, 2026 · CVE Program (cve.org) e CISA ADP
  • SSVC assessment updated
    Oct 13, 2026 · CVE Program (cve.org) e CISA ADP
  • Record published
    Oct 13, 2026
  • Fix documented
    Oct 13, 2026 · NIST National Vulnerability Database
  • CVSS changed · 9.6
    Oct 13, 2026 · NIST National Vulnerability Database
  • Source status changed · → Analyzed
    Oct 13, 2026 · NIST National Vulnerability Database
  • Record created in this database
    Oct 13, 2026 · NIST National Vulnerability Database
  • CVE published
    Feb 4, 2026 · GitHub_M

Source activity

Repeated readings are counted rather than listed.

  • 1× Official description updated · Oct 13, 2026 – Oct 13, 2026

References

3 on the record

Elsewhere on this site

Langroid
every CVE for this vendor
Injection
same class
CWE-94
other pages naming this weakness

Related CVEs (same products)

  • CVE-2026-50180 Langroid: SQLChatAgent _validate_query blocklist misses pg_read_file family enabling arbitrary file read Jul 9, 2026
  • CVE-2026-50181 Langroid: Path traversal in the file tools allows read/write outside configured current directory Jul 9, 2026
  • CVE-2026-54760 Langroid: SQLChatAgent dangerous-function blocklist can be bypassed with quoted or schema-qualified pg_read_file calls Jul 9, 2026
  • CVE-2026-54769 Langroid: Sandbox Escape to Remote Code Execution via Incomplete `eval()` Mitigation in TableChatAgent Jul 9, 2026
  • CVE-2026-54771 Langroid: handle_message() executes user-supplied tool JSON without sender verification Jul 9, 2026
  • CVE-2026-55615 Langroid: Neo4jChatAgent executes LLM-generated Cypher without validation (prompt-to-Cypher injection; config-conditional RCE), mirroring the SQLChatAgent bug fixed in CVE-2026-25879 Jul 9, 2026

Not in any source we poll

Listed rather than left blank: an empty field and an unmeasured one look identical on screen, and only one is a reason to look elsewhere.

  • No confirmed IOCs, IP addresses, domains, file hashes, or malware artifacts supplied.
  • No organization-specific asset inventory, compensating-control status, or patch deployment evidence supplied.
  • No exploit packet captures, log samples, or incident case IDs supplied.

Answered from this record

Text assembled only from the fields above — no additional claims.

What should defenders know first?

CVE-2026-25481 is "Langroid code injection via TableChatAgent pandas_eval filter bypass (CWE-94)", rated Critical. It affects Langroid (Langroid); versions are in the scope table. It is not in CISA KEV, which does not rule out exploitation. CVSS 9.6 describes technical severity. EPSS 0.82% estimates the probability of exploitation in 30 days; neither replaces your asset context. First verify whether exposed or business-critical assets run the affected versions, apply vendor fixes or mitigations, and preserve logs for review.

Comments

Moderated technical discussion. Read the community guidelines.

No comments yet.

Sign in or create an account to comment and suggest corrections.