← Back
CVE-2025-6209
Vulnerability in llama-index (CVE-2025-6209)
Summary
vulnerability in llama-index (CVE-2025-6209). Confidential information can be exposed externally. Exploitable via ``encode_image``. Mitigation: upgrade to `cdeaab91a204d1c3527f177dac37390327aef274, 0.12.41` or later.
AI summary snake-internal / snake-material-v2
A vulnerability tracked as **CVE-2025-6209** has been found in llama-index.
Attackers can target a specific entry point like ``encode_image`` over the network to misuse the product.
Confidential information can be exposed externally. CVSS score: ?/10.
What to do: upgrade llama-index to **cdeaab91a204d1c3527f177dac37390327aef274, 0.12.41** or later.
If unsure, ask your IT team or search "llama-index CVE-2025-6209" on the vendor's site.
CVE-2025-6209 (llama-index) — CWE-29 /
Attack vector: remote (network-reachable) / unauthenticated / no user interaction
Attack surface: `encode_image` / `generic_utils.py` / `image_path`
Patched: `cdeaab91a204d1c3527f177dac37390327aef274, 0.12.41` — apply immediately
Plan: 1) Audit SBOM/dependencies, 2) Stage→prod upgrade, 3) Add WAF/proxy monitoring on affected endpoints, 4) Hunt IOCs in logs.
Refs: see the GHSA / vendor advisory / patched release linked on this page.
❓ What is the problem
**A vulnerability** (CWE-29) exists in llama-index. Attackers reach the vulnerable code path via ``encode_image`` without authentication.
📍 Affected scope
llama-index — . Attack surface: `encode_image` / `generic_utils.py` / `image_path`.
🔥 Severity
Severity: ?. Confidential information can be exposed externally
🔧 How to fix
Update to **cdeaab91a204d1c3527f177dac37390327aef274, 0.12.41**.
🛡️ Workaround
Until the patch is applied: disable the affected feature, apply WAF rules, or restrict access via network ACLs.
🔍 Detection
Search webserver/proxy logs for unusual request patterns matching this CVE's known IOCs. Run `grep -r 'llama-index' .` against your dependency files (package-lock.json, requirements.txt, go.sum) to find affected services.
Response Actions (7 steps)
Concrete steps and command examples for SOC/SRE teams to execute in order
-
1Identify exposure identify
grep -r 'llama-index' . | grep -v node_modulesリポジトリと本番環境の依存ファイル (package-lock.json / requirements.txt / go.sum / Gemfile.lock 等) で `llama-index` を grep し、稼働しているサービス・バージョンを把握する。
-
6Apply patch patch
Upgrade llama-index to cdeaab91a204d1c3527f177dac37390327aef274, 0.12.41ステージング環境で cdeaab91a204d1c3527f177dac37390327aef274, 0.12.41 に上げて回帰テスト → 本番反映。回帰テストはアプリの主要ハッピーパスと、Step 3 で見つけた異常検知の続報チェックを含めること。
-
7Post-deployment verification verify
Confirm patched version is live in productionパッチ適用後、ステージングで PoC または同等の悪用パターンを再現して脆弱性が閉じたことを確認。本番では Step 3 と同じログクエリでアラート再発が無いか継続監視。
Affected packages
PyPI
llama-index
[{"repo":"https:\/\/github.com\/run-llama\/llama_index","type":"GIT","events":[{"introduced":"0"},{"fixed":"cdeaab91a204d1c3527f177dac37390327aef274"}]},{"type":"ECOSYSTEM","events":[{"introduced":"0.12.27"},{"fixed":"0.12.41"}]}]
PyPI
llama-index-core
[{"type":"ECOSYSTEM","events":[{"introduced":"0.11.23"},{"fixed":"0.12.41"}]}]
References
- advisory https://nvd.nist.gov/vuln/detail/CVE-2025-6209
- advisory https://github.com/advisories/GHSA-2rhq-96q8-4vjq
- package https://github.com/run-llama/llama_index
- package https://pypi.org/project/llama-index-core
- web https://github.com/run-llama/llama_index/commit/cdeaab91a204d1c3527f177dac37390327aef274
- web https://huntr.com/bounties/e89d14f8-bfe8-4c9a-bb2a-656c01cc9a68
- web https://github.com/pypa/advisory-database/tree/main/vulns/llama-index/PYSEC-2025-65.yaml