CVE-2026-107717Medium· 6.5▾ SunlitBanks generates meaningful LLM prompts using a simple template language. Prior to 2.5.0, Banks Prompt.chat_messages() attempts to parse every line of rendered template output as ChatMessage JSON. When an application renders untrusted dat…
▾ Sunlit zone — Low / medium · no exploitation signal
impact 35.8 · likelihood 0 · exploitation 0
Need a working PoC? Pro members can cast a request and our team develops one — it lands right here.
Banks generates meaningful LLM prompts using a simple template language. Prior to 2.5.0, Banks Prompt.chat_messages() attempts to parse every line of rendered template output as ChatMessage JSON. When an application renders untrusted data and passes the returned ChatMessage objects to an LLM provider, attacker-controlled JSON can cross the prompt boundary and become a system, assistant, or tool message because ChatMessage.role accepts arbitrary strings. This can override application instructions, alter the intended prompt structure, or confuse downstream tool and message handling. This issue is fixed in version 2.5.0.
Refer to the linked advisories for vendor-supplied fixes and affected version ranges.
Affected packages:
banks <= 2.4.5Patched in:
banks 2.5.0Connected by shared product, vendor, weakness, or advisory.
CVE-2026-107716MediumBanks generates meaningful LLM prompts using a simple template language
CVE-2026-71492Medium· 6.5Banks generates meaningful LLM prompts using a simple template language
CVE-2026-44209High· 7.5banks has Critical Remote Code Execution (RCE) via Jinja2 SSTI
CVE-2021-36325High· 7.5Dell BIOS contains an improper input validation vulnerability
CVE-2021-36323High· 7.5Dell BIOS contains an improper input validation vulnerability
CVE-2021-36324High· 7.5Dell BIOS contains an improper input validation vulnerability