Machine-written summary
Summary written by Claude Haiku from the source advisory. Not reviewed by a person.
Affected: praisonaiagents versions before 1.5.115. Two issues exist in its MultiAgentLedger and MultiAgentMonitor components: agents sharing an ID can share a ledger, exposing context such as system prompts and conversation history, and agent IDs used in file paths are not sanitized, allowing path traversal. An attacker who can register agents could read or write arbitrary files, or access another agent's context. Upgrade to version 1.5.115.
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 |
|---|---|---|---|---|
| 8.7 | High | 4.0 | CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N | CNA (VulnCheck) |
- CISA KEV Not listed.
- EPSS 0.0092, the 60th percentile, on 16 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.
Timeline
- 18 Jun 2026, 22:12 UTC Confirmed by the CVE List
- 31 Oct 2026, 15:02 UTC First seen by agentprime
- 31 Oct 2026, 15:02 UTC Confirmed by OSV
Sources
- GitHub Advisory Database: GHSA-766v-q9x3-g744
- OSV: GHSA-766v-q9x3-g744
- github.com/MervinPraison/PraisonAI/security/advisories/GHSA-766v-q9x3-g744
- nvd.nist.gov/vuln/detail/CVE-2026-56078
- github.com/MervinPraison/PraisonAI
- www.vulncheck.com/advisories/praisonai-arbitrary-file-read-and-write-via-path-traversal-in-multiagentmonitor