PYSEC-2026-4202 Banks: User-controlled prompt input can be parsed as privileged chat messages

Summary Banks' Prompt.chatmessages 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...

Banks: User-controlled prompt input can be parsed as privileged chat messages

Summary Banks' Prompt.chatmessages 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...

CVE-2026-107717

A flaw was found in banks. When generating chat messages for Large Language Models LLMs, the library attempts to parse every rendered template line as structured data without restricting message roles. A remote attacker can exploit this flaw by submitting crafted input that is interpreted as...

CVE-2026-107716

A flaw was found in Banks. The directory prompt registry fails to properly validate symbolic links file system shortcuts that point to another location. An attacker with the ability to influence files in the prompt directory can exploit this vulnerability by creating links that point outside the...

CVE-2026-107716

Banks generates meaningful LLM prompts using a simple template language. Prior to 2.5.1, Banks DirectoryPromptRegistry does not reject symbolic links for index.json or discovered and existing .jinja prompt files. In an application where untrusted users can influence a prompt directory,...

CVE-2026-107717

Banks generates meaningful LLM prompts using a simple template language. Prior to 2.5.0, Banks Prompt.chatmessages 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 provide...

GHSA-556J-VV39-8RQV Banks: Symlink traversal and arbitrary file disclosure/overwrite in DirectoryPromptRegistry

Summary In banks.registries.DirectoryPromptRegistry, prompt file paths and the index file index.json do not refuse symbolic links. When a prompt directory contains or accepts untrusted files e.g. unpacked archives, shared repositories, or multi-tenant folders, symbolic links pointing outside the...

voice-agent-tequity (>=0.1.0, <=0.1.1) potentially affected by CVE-2026-107717 via banks (2.2.0)

banks PYPI version 2.2.0 is affected by a known vulnerability. The following packages have a transitive dependency on banks and may be impacted: - voice-agent-tequity =0.1.0, =0.1.1 Source cves: CVE-2026-107717 Source advisory: GHSA-HMQ2-7HP6-7CRH...

voice-agent-tequity (>=0.1.0, <=0.1.1) potentially affected by CVE-2026-107717 via banks (2.2.0)

banks PYPI version 2.2.0 is affected by a known vulnerability. The following packages have a transitive dependency on banks and may be impacted: - voice-agent-tequity =0.1.0, =0.1.1 Source cves: CVE-2026-107717 Source advisory: OSV:GHSA-HMQ2-7HP6-7CRH...

Banks: User-controlled prompt input can be parsed as privileged chat messages

Summary Banks' Prompt.chatmessages 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...

GHSA-HMQ2-7HP6-7CRH Banks: User-controlled prompt input can be parsed as privileged chat messages

Summary Banks' Prompt.chatmessages 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...

Improper Neutralization of Special Elements in Output Used by a Downstream Component ('Injection')

Overview banks is an A prompt programming language Affected versions of this package are vulnerable to Improper Neutralization of Special Elements in Output Used by a Downstream Component 'Injection' via Prompt.chatmessages, which parsed every line of a rendered template as a possible ChatMessage...

CVE-2026-107717

Banks generates meaningful LLM prompts using a simple template language. Prior to 2.5.0, Banks Prompt.chatmessages 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 provide...

voice-agent-tequity (>=0.1.0, <=0.1.1) potentially affected by CVE-2026-107717 via banks (2.2.0)

banks PYPI version 2.2.0 is affected by a known vulnerability. The following packages have a transitive dependency on banks and may be impacted: - voice-agent-tequity =0.1.0, =0.1.1 Source cves: CVE-2026-107717 Source advisory: MEND:CVE-2026-107717...

CVE-2026-107717

The Banks library (prior to version 2.5.0 ) is vulnerable to a prompt injection flaw in the Prompt.chat_messages() function. The issue stems from the software attempting to parse every line of rendered template output as ChatMessage JSON . Because ChatMessage.role accepts arbitrary strings, an at...

EUVD-2026-95341

Banks generates meaningful LLM prompts using a simple template language. Prior to 2.5.0, Banks Prompt.chatmessages 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 provide...

CVE-2026-107717 Banks: User-controlled prompt input can be parsed as privileged chat messages

Banks generates meaningful LLM prompts using a simple template language. Prior to 2.5.0, Banks Prompt.chatmessages 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 provide...

CVE-2026-107717 Banks: User-controlled prompt input can be parsed as privileged chat messages

Banks generates meaningful LLM prompts using a simple template language. Prior to 2.5.0, Banks Prompt.chatmessages 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 provide...

CVE-2026-107717 Banks: User-controlled prompt input can be parsed as privileged chat messages

Banks generates meaningful LLM prompts using a simple template language. Prior to 2.5.0, Banks Prompt.chatmessages 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 provide...

CVE-2026-107716 Banks: Symlink traversal and arbitrary file disclosure/overwrite in DirectoryPromptRegistry

Banks generates meaningful LLM prompts using a simple template language. Prior to 2.5.1, Banks DirectoryPromptRegistry does not reject symbolic links for index.json or discovered and existing .jinja prompt files. In an application where untrusted users can influence a prompt directory,...