CVE-2026-56838PraisonAI recipe.run_stream skips dangerous-tool policy enforcement
Updated under an hour ago ()
Does this affect you?
It affects MervinPraison PraisonAI. Add what you run to find out whether that includes you.
EPSS puts the chance of exploitation in the next 30 days at 0.15%, higher than 4% of scored CVEs.
Do this next
Free account, 1 product
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
- 7.8 HIGH (v3.1, CNA)CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
- Weakness (CWE)
- CWE-78, CWE-693, CWE-863
- Known exploited
- Not in CISA's KEV catalog
- EPSS (exploitation in the next 30 days)
- 0.15% (percentile 4)
- Assigned by
- GitHub_M
- NVD analysis
- Deferred
- Record last updated
- Oct 23, 2026
- First seen by InfoSec Signals
- Oct 23, 2026
The CVE record on cve.org NVD's entry
The CVE record is authoritative. Products marked “from the name” were identified from the CNA's free-text names, not a CPE, and are matched less certainly. This product uses the NVD API but is not endorsed or certified by the NVD.