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
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
- Chat MessagesT1552.008
Indicators of compromise
- CVE-2026-107717cve
Original source: https://github.com/advisories/GHSA-hmq2-7hp6-7crh