CVE-2026-61437 json
PraisonAI before 1.6.78 Remote Code Execution via tools.py
published 2026-07-10 4 mo ago modified 2026-10-25 14 d ago also EUVD-2026-42900 , GHSA-4gfv-wg42-7jw5 , PYSEC-2026-4267
- cvss
- 7.8
- version 3.1, CNA
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 0.2%
- EPSS 0.2% chance of exploitation in 30 days, percentile 9%
- public exploits
- 0
- none known
Summary
PraisonAI (pip package praisonaiagents) before 1.6.78 contains an unsafe dynamic module loading vulnerability in AgentFlow._resolve_pydantic_class (src/praisonai-agents/praisonaiagents/workflows/workflows.py). When a workflow step uses a string output_pydantic reference, the framework locates and imports a sibling tools.py from the workflow file's directory via importlib exec_module without sandboxing, ignoring the PRAISONAI_ALLOW_*_TOOLS environment variables. An attacker who controls a workflow file and its sibling tools.py can execute arbitrary Python code with the workflow runner's privileges when the workflow is executed via WorkflowManager or after load_yaml.
Patch / fix
- pypi praisonaiagents 1.6.78
- MervinPraison PraisonAI 1.6.78
CISA SSVC
- Exploitation
- Proof of concept is public
- Automatable
- no
- Technical impact
- total
- Assessed
- 3 mo ago
Exploit prediction
0.20% chance of exploitation in the next 30 days, higher than 9% of all scored CVEs (FIRST EPSS, 2026-11-08).
Exploits and checks
- github.com https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-4gfv-wg42-7jw5 referenced PoC, tagged "exploit" by a source, unverified
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CNA | 4.0 | 8.5 | CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N |
| CNA | 3.1 | 7.8 | CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H |
| GitHub | 3.1 | 7.8 | CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H |
| CNA | 4.0 | 8.5 | CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X |
| OSV | 3.1 | 7.8 | CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H |
Affected packages
| ecosystem | package | affected | fixed in |
|---|---|---|---|
| pypi | praisonaiagents | <1.6.78 |
1.6.78 |
Affected products
- MervinPraison PraisonAI
Classification
References
-
github.com
/MervinPraison/PraisonAI/security/advisories/GHSA-4gfv-wg42-7jw5
vendor-advisory, exploit, web
-
vulncheck.com
/advisories/praisonai-before-remote-code-execution-via-tools-py
third-party-advisory, web
-
nvd.nist.gov
/vuln/detail/CVE-2026-61437
advisory
-
github.com
/MervinPraison/PraisonAI
package
-
pypi.org
/project/praisonaiagents
package
-
github.com
/advisories/GHSA-4gfv-wg42-7jw5
advisory
Sources
- CVE List CVE-2026-61437
- GitHub Advisory GHSA-4gfv-wg42-7jw5
- NVD CVE-2026-61437
- OSV PYSEC-2026-4267
Fencer Vulns 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.