CriticalVulnerabilityLLM-specific
CVE-2025-9556: Langchaingo server side template injection through prompt parsing
- Source
- NVD(opens in a new tab)
- Identifier
- CVE-2025-9556
- Published
- Record updated
- Known exploitation
- Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
- EPSS
- 0.7%
Summary
CVE-2025-9556 affects langchaingo, which supports jinja2 syntax in prompt parsing via the gonja library v1.5.3. Gonja's include and extends directives can read files, creating a server side template injection that lets an attacker insert a statement into a prompt to read the "etc/passwd" file.
Mitigation
The source does not state a fix yet. Check the original advisory for updates.
Related items
- MediumCVE-2026-121936: easyVoice server-side request forgery through openaiBaseUrl in /api/v1/ttsSimilar attack · NVD/CVE Database
- MediumCVE-2026-118628: MLflow get-artifacts server-side request forgery information disclosureSimilar attack · NVD/CVE Database
- HighCVE-2026-118625: MLflow Tracking Server privilege escalation via get_endpointsSimilar attack · NVD/CVE Database
- InfoWhen trust becomes the payload: Inside the threats, etc quarterly reportSimilar attack · Elastic Security Labs
- MediumCritical Langflow flaws enable authentication bypass and RCESimilar attack · CSO Online