CVE-2026-39891 json
PraisonAI has a Template Injection in Agent Tool Definitions
published 7mo ago modified 3mo ago also EUVD-2026-20639 , GHSA-hwg5-x759-7wjg , PYSEC-2026-2917
- cvss
- 8.8
- version 3.1, CNA
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 0.6%
- EPSS 0.6% chance of exploitation in 30 days, percentile 47%
- public exploits
- 0
- none known
Summary
PraisonAI is a multi-agent teams system. Prior to 4.5.115, the create_agent_centric_tools() function returns tools (like acp_create_file) that process file content using template rendering. When user input from agent.start() is passed directly into these tools without escaping, template expressions in the input are executed rather than treated as literal text. This vulnerability is fixed in 4.5.115.
Patch / fix
- pypi praisonai 4.5.115
- praison praisonai 4.5.115
Is CVE-2026-39891 in your dependencies? Fencer shows which of your repositories are affected as soon as an advisory lands, and opens the fix as a pull request.
Check with FencerCISA SSVC
- Exploitation
- Proof of concept is public
- Automatable
- no
- Technical impact
- total
- Assessed
- 7mo ago
Exploit prediction
0.57% chance of exploitation in the next 30 days, higher than 47% of all scored CVEs (FIRST EPSS, 2026-11-09).
Exploits and checks
- github.com https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-hwg5-x759-7wjg referenced PoC, tagged "exploit" by a source, unverified
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CNA | 3.1 | 8.8 | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H |
| GitHub | 3.1 | 8.8 | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H |
| OSV | 3.1 | 8.8 | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H |
Affected packages
| ecosystem | package | affected | fixed in |
|---|---|---|---|
| pypi | praisonai | <4.5.115 |
4.5.115 |
Affected products
- MervinPraison PraisonAI
Classification
- Weakness
-
- CWE-94 Improper Control of Generation of Code
References
-
github.com
/MervinPraison/PraisonAI/security/advisories/GHSA-hwg5-x759-7wjg
exploit, web, vendor-advisory
-
nvd.nist.gov
/vuln/detail/CVE-2026-39891
advisory
-
github.com
/MervinPraison/PraisonAI
package
-
github.com
/MervinPraison/PraisonAI/releases/tag/v4.5.115
web
-
pypi.org
/project/praisonai
package
-
github.com
/advisories/GHSA-hwg5-x759-7wjg
advisory
Sources
- CVE List CVE-2026-39891
- GitHub Advisory GHSA-hwg5-x759-7wjg
- NVD CVE-2026-39891
- OSV PYSEC-2026-2917
Fencer Intel keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.
CPEs and fixed versions use Anchore's correction of NVD's data: Added CPE configurations because not yet analyzed by NVD.