CVE-2026-61445
Authenticated chat prompt allows arbitrary file write and root command execution in PraisonAI AICoder.
Is CVE-2026-61445 being exploited?
Not confirmed. CVE-2026-61445 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 0.88% probability of exploitation in the next 30 days.
How severe is CVE-2026-61445?
CVE-2026-61445 is rated Critical with a CVSS score of 9.4. 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-2026-61445?
Yes. A fix has been recorded for CVE-2026-61445. The vendor advisory is the authority on the exact fixed version — apply it from there rather than from a summary.
What does CVE-2026-61445 affect?
CVE-2026-61445 affects PraisonAI < 4.6.78, AICoder component, LLM chat interface, Servers hosting PraisonAI (Linux/Unix). Confirm the exact affected versions against the vendor advisory before deciding you are exposed.
What should I do about CVE-2026-61445?
Upgrade to 4.6.78+, restrict chat access, audit logs, rotate credentials
Exploitation status reflects CISA's KEV catalog as we last synced it. Check the catalog directly.
Attackers can write files and execute arbitrary shell commands as root via crafted prompts to the AICoder LLM tool.
Immediate action required
- affected< 4.6.78
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.