Vulnerability · Published Jul 9, 2026 · Assigned by GitHub_M
CVE-2026-54760Langroid: SQLChatAgent dangerous-function blocklist can be bypassed with quoted or schema-qualified pg_read_file calls
Critical 9.3
In plain English
A critical-severity path traversal in langroid from langroid. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.6% (higher than 51% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.
Official description
Langroid is a framework for building large-language-model-powered applications. Prior to version 0.65.1, the `SQLChatAgent` SQL-injection mitigation, with default `allow_dangerous_operations=False`, combines a raw-text regex blocklist (`_DANGEROUS_SQL_PATTERNS`) with a `sqlglot` SELECT-only statement allowlist. The blocklist entries that target callable functions require the function name to be immediately followed by `\s*\(`. PostgreSQL accepts the same call with the name separated from `(` by a quoted identifier, an inline comment, or schema qualification. These forms evade the regex, still parse as `SELECT`, and execute the same PostgreSQL function. This restores the `pg_read_file` server-side file-read primitive that the prior CVE-2026-25879 / GHSA-pmch-g965-grmr fix was meant to block: the parent advisory fixed a missing `pg_read_file` blocklist entry, while this report shows that the added regex is bypassable. Version 0.65.1 fixes the issue.
Affected packages & fixed versions
| Ecosystem | Package | Fixed in | Advisory |
|---|---|---|---|
| PyPI | langroid | 0.65.1 | GHSA-6xc5-4r68-67fc |
| PyPI | langroid | 0.65.1 | PYSEC-2026-2577 |
Affected products (as reported)
Weakness: CWE-22, CWE-89 · Vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
References
- https://github.com/langroid/langroid/security/advisories/GHSA-6xc5-4r68-67fc x_refsource_CONFIRM