ai_security▌

2026-11-18

3 item(s) verified and swept on 2026-11-18, each citing a primary source.

NOTABLECVE

SQLBot CVE-2026-130595 (GHSA-f9wg-44c5-frh4): denylist key mismatch lets users steer LLM-generated SQL past the read-only check into host file reads and writes

SQLBot 1.10.0-1.10.3 never applies its PostgreSQL dangerous-function denylist because the denylist is keyed 'postgresql' while lookups use 'pg', so an authenticated user can steer the LLM-generated SQL past check_sql_read() with pg_read_file, pg_write_file, lo_import or lo_export and read or write files on the database host.

NOTABLESUPPLY-CHAIN

Phrack 73: reproducible Trusting-Trust attack with a backdoored helper model that writes its own poison into the next model's training data

Phrack issue 73 publishes a reproducible end-to-end attack on LLM training pipelines: a trigger-backdoored Qwen2.5-3B "helper" model used for SFT data processing recognizes data-processing tasks and inserts trigger-conditional malicious behavior into the data it emits, so the backdoor re-propagates into every model trained on that processed corpus - Thompson's self-reproducing compiler backdoor moved to the AI supply chain.

NOTABLETOOL

Phrack 73: LLM agents audit, PoC and exploit a previously unknown Linux crypto-subsystem flaw through to a working Fedora 43 exploit

In the companion Phrack 73 article, researchers Juefei Pu, Yifan Wu, Kareem Shehada and Zhiyun Qian document how LLM agents audited code, generated proofs of concept and carried the tedious steps of finding a previously unknown flaw in the Linux crypto subsystem and riding it to a working exploit on Fedora 43 - published as a first-person research write-up alongside their self-propagating-poison paper in the same issue.

← 2026-11-19 · 2026-11-17 → · all days