THREATOPS
THREAT OPS › Threat News › [GHSA] GHSA-hmq2-7hp6-7crh (medium) — Banks: User-controlled prompt input can be parsed as privileged chat messages

[GHSA] GHSA-hmq2-7hp6-7crh (medium) — Banks: User-controlled prompt input can be parsed as privileged chat messages

medgithub_advisoriesPublished 2026-10-08

GHSA-hmq2-7hp6-7crh Severity: medium CVE: CVE-2026-107717

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

## 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 privilege

MITRE ATT&CK techniques

Indicators of compromise

Original source: https://github.com/advisories/GHSA-hmq2-7hp6-7crh