Vulnerability in banks (CVE-2026-107717)
Summary
Vulnerability in banks (CVE-2026-107717). Risk of unauthorized operations or information disclosure. Exploitable via ChatMessage. Mitigation: upgrade to 2.5.0 or later.
Original description
The description as published by the source.
Summary
Banks' Prompt.chat_messages() method parses every rendered output line as a potential ChatMessage JSON
object. If attacker-controlled template data renders to JSON such as {"role":"system","content":"..."},
Banks returns it as a privileged system message instead of treating it as plain user-controlled text.
Applications that render untrusted user input with Prompt.chat_messages() and pass the returned messages
directly to an LLM provider may be vulnerable to chat role injection and prompt boundary bypass.
Details
The issue is in src/banks/prompt.py:
messages: list[ChatMessage] = []
for line in rendered.strip().split("\n"):
try:
messages.append(ChatMessage.model_validate_json(line))
except ValidationError:
# Ignore lines that are not a message
pass
if not messages:
# fallback, if there was no {% chat %} block in the template,
# try to build a list of messages for the role "user"
messages.append(chat_message_from_text(role="user", content=rendered))
The method first renders the template, then attempts to parse each rendered line as a ChatMessage.
Because this parsing is applied to the final rendered output, user-controlled template variables can
accidentally become trusted structured chat messages.
The ChatMessage model also accepts any string as the role in src/banks/types.py:
class ChatMessage(BaseModel):
role: str…
Source: GitHub Security Advisories (Global) NVD GitHub Advisory
Auto-generated summary
Assembled by SecPulse from the source data (CVSS, CWE, affected versions) using templates — no AI involved. Check the original description and references below for exact details.
A vulnerability tracked as CVE-2026-107717 has been found in banks.
Attackers can target a specific entry point like ChatMessage over the network to misuse the product.
Risk of unauthorized operations or information disclosure. CVSS score: 6.5/10.
What to do: upgrade banks to 2.5.0 or later.
If unsure, ask your IT team or search "banks CVE-2026-107717" on the vendor's site.
CVE-2026-107717 (banks) — CWE-20 / CVSS v3 6.5
Attack vector: remote (network-reachable) / unauthenticated / no user interaction
Attack surface: ChatMessage / system
Patched: 2.5.0 — 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.
A vulnerability (CWE-20) exists in banks. Attackers reach the vulnerable code path via ChatMessage without authentication.
Check the vendor advisory for the affected versions of banks. Attack surface: ChatMessage / system.
Severity: Medium (CVSS 6.5/10). Risk of unauthorized operations or information disclosure.
Update to 2.5.0.
Until the patch is applied: disable the affected feature, apply WAF rules, or restrict access via network ACLs.
Search webserver/proxy logs for unusual request patterns matching this CVE's known IOCs. Run grep -r 'banks' . against your dependency files (package-lock.json, requirements.txt, go.sum) to find affected services.
Response actions
Concrete steps and command examples for SOC/SRE teams to execute in order
-
1Identify exposure identify
grep -r 'banks' . | 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
banksを grep し、稼働しているサービス・バージョンを把握する。 -
2Apply patch patch
Upgrade banks to 2.5.0ステージング環境で 2.5.0 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を含めること。
-
3Post-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。本番ではアクセスログ・WAF でアラート再発が無いか継続監視。