High · CVSS 7.8CVE-2026-56838

PraisonAI recipe.run_stream skips dangerous-tool policy enforcementCVE-2026-56838

Answer in brief

CVE-2026-56838 records a High severity (CVSS 7.8) vulnerability in PraisonAI recipe.run_stream skips dangerous-tool policy enforcement. The current sources do not mark it as known exploited. The current feed maps MervinPraison/PraisonAI (generic). Check affected ranges and fixed versions before updating.

Analysis pending evidence review

HOL Guard separates source facts from reviewed analysis. See the methodology.

Published Oct 23, 2026Updated Oct 23, 2026Source checked Oct 23, 2026First seen by HOL Oct 23, 2026Material review Oct 23, 2026

Upstream Advisory

Key facts

Risk: High · CVSS 7.8
Exploitation: Not marked as known exploited
Affected software: 1 mapped package or product
Fix availability: Available

Why this deserves its current priority

CVSS is 7.8. The current sources do not mark it as known exploited. Treat this as a source-backed prioritization signal, not a statement about your environment.

Analysis status

Analysis pending evidence review

Factual feed record only; HOL analysis is not approved for indexing. Read the methodology.

Affected scope and exposure questions

The current feed maps MervinPraison/PraisonAI (generic). Check affected ranges and fixed versions before updating.

Mapped affected packages and fixed versions
Package	Affected range	Fixed version
MervinPraison/PraisonAIgeneric	>=4.5.87 <4.6.59	4.6.59

Recommended response

Check inventory. Check lockfiles and deployed manifests for MervinPraison/PraisonAI.
Review the reported fix. Update MervinPraison/PraisonAI to 4.6.59 if you use the affected versions. Test the change in a non-production environment first.

Evidence timeline and material changes

Published upstream
Oct 23, 2026
Evidence: source:cvelist:source_dates:source-dates:record
Source modified
Oct 23, 2026
Evidence: source:cvelist:source_dates:source-dates:record
First seen by HOL
Oct 23, 2026

Sources and claim methodology

GitHub security advisorygithub.com

Upstream source description

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.

Quoted source text, attributed separately from HOL analysis.