Skip to content
Patch Next
Sign inAdd to your agent

← Actionable
Medium, CVSS 5.5amended

PraisonAI: Coarse-Grained Tool Approval Cache Bypasses Per-Invocation Consent for Shell Commands

CVE-2026-56074GHSA-ffp3-3562-8cv3

What to do

Vendor fix available. Upgrade each affected package to the fixed version on its release line (praisonaiagents 4.5.128), redeploy, then verify what is actually installed.

This page has no inventory attached, so it cannot say whether you are affected. A vendor fix is not proof that your deployment is fixed.

Add to your agent

Affected packages

Sources

Severity and exploitation
Exploitation
No confirmed exploitation recorded. Patch Next marks exploitation only from CISA KEV.
CVSS
5.5 · CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:N/A:N
EPSS
  • CVE-2026-56074: 0.18% estimated exploitation activity in the next 30 days; percentile 7.16 (FIRST EPSS, 2026-11-03). This is a model estimate, not proof of exploitation or customer exposure.
Source description

As published by the source; long descriptions are shortened.

Summary The approval system in PraisonAI Agents caches tool approval decisions by tool name only, not by invocation arguments. Once a user approves executecommand for any command (e.g., ls -la), all subsequent executecommand calls in that execution context bypass the approval prompt entirely. Combined with os.environ.copy() passing all process environment variables to subprocesses, this allows an LLM agent (potentially via prompt injection) to silently exfiltrate API keys and credentials without further user consent. Details The requireapproval decorator in src/praisonai-agents/praisonaiagents/approval/init.py:176-178 checks approval status by tool name only: The markapproved function in registry.py:144-147 stores only the tool name string: The approval context is never cleared during agent execution — clearapproved() exists (registry.py:152) but is never called in the agent's tool execution path (agent/toolexecution.py). Meanwhile, the ConsoleBackend UI at backends.py:95-96 misleads…

Dates and revisions
Published by the source
Last modified by the source
Source last checked
  1. Revision 7 · amended ·

    Amended from osv record PYSEC-2026-2946

  2. Revision 6 · amended ·

    Amended from osv record PYSEC-2026-2946

  3. Revision 5 · amended ·

    Amended from osv record PYSEC-2026-2946

  4. Revision 4 · amended ·

    Amended from osv record PYSEC-2026-2946

  5. Revision 3 · amended ·

    Amended from ghsa record GHSA-ffp3-3562-8cv3

  6. Revision 2 · amended ·

    Amended from osv record PYSEC-2026-2946

  7. Revision 1 · created ·

    Published from osv record GHSA-ffp3-3562-8cv3

Agent brief

Preview the exact text before you copy it. Commands are read-only suggestions; review them before running anything.

# Patch Next advisory brief: CVE-2026-56074

Advisory: PraisonAI: Coarse-Grained Tool Approval Cache Bypasses Per-Invocation Consent for Shell Commands
IDs: CVE-2026-56074, GHSA-ffp3-3562-8cv3
Record: https://patchnext.com/advisories/cve-2026-56074 (revision 7, source checked 4 Nov 2026, 06:20 UTC)
Inventory: none attached. This brief comes from a public page and does not say whether any deployment is affected.
Severity: Medium (CVSS 5.5)
Exploitation: no confirmed exploitation recorded. Patch Next confirms exploitation only from CISA KEV.
Vendor response: Vendor fix available; fixed versions by package: praisonaiagents 4.5.128. A vendor fix does not mean a deployment is fixed.

## Affected components
- PyPI praisonaiagents: affected < 4.5.128; fixed in 4.5.128

## Suggested inspection (read-only)
- `python -m pip show praisonaiagents`: prints the installed version. Run with the environment that serves production active.

## Supported action
Upgrade each affected component to a fixed version on its release line. For a transitive dependency, upgrade the parent package or add an override or constraint, then regenerate the lockfile. Redeploy every environment that ran an affected version.

## Required regression checks
- Run the test suite and a production build.
- Exercise the features that depend on praisonaiagents.
- Repeat the inspection and confirm that only fixed versions remain installed.

## Rollback considerations
- Keep the previous lockfile and deployment artifact. Rolling back reinstates the vulnerable version, so apply any documented mitigation while you fix forward.

## Unresolved questions
- Which deployments run an affected version?
- Exploitation status can change. Check again before lowering the priority.
- Mark the work resolved only after the fixed version is verified in production.

## Sources
- Verified: https://osv.dev/vulnerability/GHSA-ffp3-3562-8cv3 (OSV record GHSA-ffp3-3562-8cv3 lists affected ranges: PyPI praisonaiagents >=0 <4.5.128 (fixed))
- Verified: https://osv.dev/vulnerability/PYSEC-2026-2946 (OSV record PYSEC-2026-2946 lists affected ranges: PyPI praisonaiagents >=0 <4.5.128 (fixed))
- Verified: https://github.com/advisories/GHSA-ffp3-3562-8cv3 (GitHub-reviewed advisory GHSA-ffp3-3562-8cv3 lists affected ranges: PyPI praisonaiagents >=0 <4.5.128)

Commands are suggestions: review each one before running it.

Loading voting…