Security Digest · Vulnerability record
CVE-2026-25481: Langroid has WAF Bypass Leading to RCE in TableChatAgent
Langroid is a framework for building large-language-model-powered applications.
CVSS 9.4 Critical EPSS 0.8% · p57
Should you act?
Critical and remotely reachable
No known exploitation yet, but it is network-reachable without credentials. This signal is computed from CISA KEV, EPSS and CVSS data; it is not an editorial verdict.
- Not in CISA KEV, but CISA’s SSVC assessment records a public proof-of-concept, so attack code exists.
- EPSS 0.8%, percentile 57: FIRST’s model estimates a 0.8% chance of exploitation activity in the next 30 days, higher than 57% of all scored CVEs (moderate). EPSS is a probability, not a verdict.
- Only applies if your dependency tree includes
langroid(PyPI) <= 0.59.31, fixed in 0.59.32. Check your lockfile, including transitive dependencies.
What it is
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 pandaseval tool to evaluate the expression. There is a WAF in langroid/utils/pandasutils.py introduced to block code injection CVE-2025-46724. However it can be bypassed due to literalok() 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.
From the GitHub advisory
Affected Scope
langroid
Vulnerability Description
CVE-2025-46724 fix bypass:
TableChatAgent can call pandaseval tool to evaluate the expression. There is a WAF in langroid/utils/pandasutils.py introduced to block code injection CVE-2025-46724. However it can be bypassed due to literalok() 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.
Weakness type: CWE-94.
Product: langroid (PyPI) · Assigned by: GitHub_M · Published: 2026-02-04
Affected and fixed versions
| Ecosystem | Package | Vulnerable | First fixed |
|---|---|---|---|
| PyPI | langroid | <= 0.59.31 | 0.59.32 |
| Vendor | Product | Affected versions (per CVE record) |
|---|---|---|
| langroid | langroid | < 0.59.32 |
Severity scores
| Scored by | CVSS | Score | Vector |
|---|---|---|---|
| GitHub_M | 4.0 | 9.4 Critical | CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H |
| GitHub | 4.0 | 9.4 | CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H |
- Attack vector: network (remotely reachable)
- Attack complexity: low
- Attack requirements: none
- Privileges required: none (no login)
- User interaction: passive
CVSS measures how bad a flaw is if exploited, not how likely exploitation is. Read it next to the exploitation data below.
Exploitation and urgency
- CISA KEV: not listed (no confirmed in-the-wild exploitation known to CISA).
- CISA SSVC assessment: exploitation poc, automatable yes, technical impact total.
- FIRST EPSS (model of 2026-10-21): 0.82% probability of exploitation activity in the next 30 days; percentile 57.
Timeline
- — GitHub-reviewed advisory GHSA-x34r-63hx-w57f published (critical)
- — CVE record last updated
- — CVE record published by GitHub_M
Sources and references
Original sources first. Version and fix details should always be confirmed against the vendor or project advisory.
Vulnerability records
- GitHub Advisory GHSA-x34r-63hx-w57f github.com
- CVE.org record CVE-2026-25481 cve.org
- NVD entry CVE-2026-25481 nvd.nist.gov
Other references from the CVE record and advisory
- github.com github.com
- github.com github.com
- github.com github.com
- github.com github.com
- pypi.org pypi.org