Machine-written summary
Summary written by Claude Haiku from the source advisory. Not reviewed by a person.
PraisonAI versions before 4.6.78 (PyPI package praisonai) expose the AICoder UI component's write_to_file and execute_command tools to the LLM without path validation or command sanitization. An attacker who can submit crafted messages in the chat interface, through prompt injection, can write files to arbitrary locations and run arbitrary shell commands, which the source says is root-level in Docker containers. Upgrade to praisonai 4.6.78 or later. The source gives no workaround.
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 |
|---|---|---|---|---|
| 9.4 | Critical | 4.0 | CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H | CNA (VulnCheck) |
- CISA KEV Not listed.
- EPSS 0.0064, the 50th 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
Sources
- GitHub Advisory Database: GHSA-9mp3-24cc-77mg
- OSV: GHSA-9mp3-24cc-77mg
- github.com/MervinPraison/PraisonAI/security/advisories/GHSA-9mp3-24cc-77mg
- nvd.nist.gov/vuln/detail/CVE-2026-61445
- github.com/MervinPraison/PraisonAI
- www.vulncheck.com/advisories/praisonai-before-arbitrary-file-write-and-command-execution