Machine-written summary
Summary written by Claude Haiku from the source advisory. Not reviewed by a person.
PraisonAI versions before 4.6.78 have a prompt-injection defense, enabled through enable_injection_defense(), that blocks only when three or more detector families match at once. Realistic single- or double-vector injections are rated HIGH and pass through unmodified, so an attacker who can supply input to the model can reach it and its tools. Upgrade praisonai to version 4.6.78 or later, which is the listed fix.
Not analysed yet
We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.
Severity and exploitation
| Score | Rating | CVSS | Vector | Source |
|---|---|---|---|---|
| 6.9 | Medium | 4.0 | CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:L/VA:N/SC:N/SI:N/SA:N | CNA (VulnCheck) |
- CISA KEV Not listed.
- EPSS 0.0027, the 18th percentile, on 7 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.
Timeline
- 31 Oct 2026, 14:08 UTC First seen by agentprime
- 31 Oct 2026, 14:08 UTC Confirmed by OSV