ai_security▌

← feed

NOTABLE

CVE-2026-123653: DeepSeek-Reasonix fed untrusted document content straight into LLM prompting

GHSA-46pp-w572-hw78: discoverDocs() in esengine DeepSeek-Reasonix up to 2.52.0 passed input used for LLM prompting without neutralization, reachable remotely; the exploit is publicly disclosed and fixed in 2.53.0 (GHSA-rated low).

released 2026-11-06 · ingested 2026-11-08T18:40Z

Sources

Primary source · corroboration

Cite this

APA

AI Security Index. (2026). CVE-2026-123653: DeepSeek-Reasonix fed untrusted document content straight into LLM prompting. AI Security Index. https://github.com/advisories/GHSA-46pp-w572-hw78

BibTeX

@misc{aisec-2026-11-06-deepseek-reasonix-doc-ingestion-prompt-injection,
  title  = {CVE-2026-123653: DeepSeek-Reasonix fed untrusted document content straight into LLM prompting},
  year   = {2026},
  howpublished = {\url{https://github.com/advisories/GHSA-46pp-w572-hw78}},
  note   = {AI Security Index item 2026-11-06-deepseek-reasonix-doc-ingestion-prompt-injection}
}