CVE-2026-77776
Auth bypass in Headroom proxy lets attackers access other users' LLM memory.
Is CVE-2026-77776 being exploited?
Not confirmed. CVE-2026-77776 does not appear in CISA's Known Exploited Vulnerabilities catalog, which records only exploitation that has been observed and reported publicly. That is evidence of absence of a report, not evidence the flaw is unattacked. EPSS currently estimates a 0.34% probability of exploitation in the next 30 days.
How severe is CVE-2026-77776?
CVE-2026-77776 is rated Critical with a CVSS score of 9.3. Severity describes how bad exploitation would be, not how likely it is: pair it with exploitation evidence before deciding what to patch first.
Is there a patch for CVE-2026-77776?
Yes. A fix has been recorded for CVE-2026-77776. The vendor advisory is the authority on the exact fixed version — apply it from there rather than from a summary.
What does CVE-2026-77776 affect?
CVE-2026-77776 affects Headroom LLM proxy, headroom/proxy handlers (openai.py), chat-completion & websocket endpoints, deployments using shipped docker-compose (0.0.0.0, no token). Confirm the exact affected versions against the vendor advisory before deciding you are exposed.
What should I do about CVE-2026-77776?
Apply vendor patch, bind to localhost, require HEADROOM_PROXY_TOKEN, close exposed ports.
Exploitation status reflects CISA's KEV catalog as we last synced it. Check the catalog directly.
Spoof x-headroom-user-id to read/write other users' stored LLM memories; enables data theft and user impersonation.
Immediate action required
- affected< 0.36.1
As published in the CVE Program record. A version outside these ranges is not a statement that it is unaffected — vendors sometimes understate a range, and distribution-backported builds carry upstream numbers that do not reflect what was patched into them.