Skip to content
Fencer Intel
medium 6.5

CVE-2026-107717 json

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

published last mo. modified 25d ago also GHSA-hmq2-7hp6-7crh , PYSEC-2026-4202 , EUVD-2026-95341

cvss
6.5
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.3%
EPSS 0.3% chance of exploitation in 30 days, percentile 27%
public exploits
0
none known

Summary

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.

Patch / fix

  • pypi banks 2.5.0

Is CVE-2026-107717 in your dependencies? Fencer shows which of your repositories are affected as soon as an advisory lands, and opens the fix as a pull request.

Check with Fencer

Vendor advisories

What the vendors themselves say about their products: affected, fixed or not affected, and what to do.

red hat product security vex CVE-2026-107717 updated cvss 6.5

banks: banks: Chat role injection via untrusted template input

  • Red Hat Exploit Intelligence exploit-intelligence/vulnerability-analysis-rhel9
    affected: workaround, no fix planned “Out of support scope”
  • Red Hat Lightspeed Core lightspeed-core/rag-tool-cpu-rhel9, lightspeed-core/rag-tool-cuda-12.9-rhel9 Red Hat OpenShift Lightspeed openshift-lightspeed/lightspeed-ocp-rag-rhel9
    affected: workaround, no fix available “Fix deferred”
  • Red Hat Ansible Automation Platform 2 ansible-automation-platform-25/lightspeed-chatbot-rhel8
    affected: workaround, no fix planned “Out of support scope”
  • Red Hat OpenShift Lightspeed openshift-lightspeed/lightspeed-service-api-rhel9, openshift-lightspeed-tech-preview/lightspeed-rag-tool-rhel9
    not affected: vulnerable code not present

Red Hat CSAF VEX © Red Hat, Inc., from https://security.access.redhat.com/data/csaf/v2/vex/; changed: reduced to product statuses and remediations. CC BY 4.0 · csaf

CISA SSVC

Exploitation
Proof of concept is public
Automatable
yes
Technical impact
partial
Assessed
27d ago

Exploit prediction

0.34% chance of exploitation in the next 30 days, higher than 27% of all scored CVEs (FIRST EPSS, 2026-11-09).

Exploits and checks

  • github.com https://github.com/masci/banks/security/advisories/GHSA-hmq2-7hp6-7crh referenced PoC, tagged "exploit" by a source, unverified

CVSS scores

assigned by version score vector
CNA 3.1 6.5 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N
GitHub 3.1 6.5 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N
OSV 3.1 6.5 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N

Affected packages

ecosystem package affected fixed in
pypi banks
<2.5.0
2.5.0

Affected products

  • masci banks

Classification

Weakness
  • CWE-20 Improper Input Validation

References

Sources

Fencer Intel keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.