CVE-2026-56838
PraisonAI is a multi-agent teams system. From version 4.5.87 to before version 4.6.59, PraisonAI recipe execution blocks default-denied dangerous tools unless the caller explicitly passes allow_dangerous_tools=True. The normal recipe.run() path enforces this with _check_tool_policy(). The streaming path, recipe.run_stream(), loads the same recipe, checks dependencies, and then calls _execute_recipe() without running the dangerous-tool policy check. As a result, a recipe that honestly declares execute_command in TEMPLATE.yaml requires.tools is denied by recipe.run(), but reaches the execution engine through recipe.run_stream() with allow_dangerous_tools=False. This issue has been patched in version 4.6.59.
- CVSS 3.1
- 7.8
CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H - EPSS
- 0.1% chance of exploitation in the next 30 days; higher than 3% of CVEs (scores of 2026-10-25)
- CWEs
- CWE-78, CWE-693, CWE-863
- Published
- Modified
- Record from
- the NVD, synced
Packages (OSV)
| Advisory | Ecosystem | Package | Affected | Fixed in |
|---|---|---|---|---|
| GHSA-v847-hxxw-3pxg | PyPI | praisonai | >=4.5.87 <4.6.59 | 4.6.59 |
| PYSEC-2026-3520 | PyPI | praisonai | >=4.5.87 <4.6.59 | 4.6.59 |