PraisonAI has Template Injection in Agent Tool Definitions

Exploitation

No confirmed exploitation recorded. Patch Next marks exploitation only from CISA KEV.

CVSS

8.8 · CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

EPSS

• CVE-2026-39891: 0.56% estimated exploitation activity in the next 30 days; percentile 46.58 (FIRST EPSS, 2026-11-03). This is a model estimate, not proof of exploitation or customer exposure.

As published by the source; long descriptions are shortened.

Summary Direct insertion of unescaped user input into template-rendering tools allows arbitrary code execution via specially crafted agent instructions. Details The createagentcentrictools() function returns tools (like acpcreatefile) that process file content using template rendering. When user input from agent.start() is passed directly into these tools without escaping (as shown in agentcentricexample.py:85-86), template expressions in the input are executed rather than treated as literal text. This occurs because: 1. No input sanitization or escaping is applied to user-controlled content 2. The ACP-enabled runtime auto-approves operations (approvalmode="auto") 3. Tools lack context-aware escaping for template syntax PoC Successful exploitation creates /tmp/pwned confirming arbitrary command execution. The expression {{77}} renders as 49 instead of literal text. Impact Attackers can execute arbitrary system commands with the privileges of the running process by injecting malicious…

Published by the source

8 Apr 2026, 19:21 UTC

Last modified by the source

13 Jul 2026, 16:43 UTC

Source last checked

26 Oct 2026, 13:40 UTC

1. Revision 2 · amended · 26 Oct 2026

   Amended from ghsa record GHSA-hwg5-x759-7wjg

2. Revision 1 · created · 24 Oct 2026

   Published from osv record GHSA-hwg5-x759-7wjg

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

# Patch Next advisory brief: CVE-2026-39891

Advisory: PraisonAI has Template Injection in Agent Tool Definitions
IDs: CVE-2026-39891, GHSA-hwg5-x759-7wjg
Record: https://patchnext.com/advisories/cve-2026-39891 (revision 2, source checked 26 Oct 2026, 13:40 UTC)
Inventory: none attached. This brief comes from a public page and does not say whether any deployment is affected.
Severity: High (CVSS 8.8)
Exploitation: no confirmed exploitation recorded. Patch Next confirms exploitation only from CISA KEV.
Vendor response: Vendor fix available; fixed versions by package: praisonai 4.5.115. A vendor fix does not mean a deployment is fixed.

## Affected components
- PyPI praisonai: affected <= 4.5.114; fixed in 4.5.115

## Suggested inspection (read-only)
- `python -m pip show praisonai`: 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 praisonai.
- 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-hwg5-x759-7wjg (OSV record GHSA-hwg5-x759-7wjg lists affected ranges: PyPI praisonai >=0 <4.5.115 (fixed))
- Verified: https://github.com/advisories/GHSA-hwg5-x759-7wjg (GitHub-reviewed advisory GHSA-hwg5-x759-7wjg lists affected ranges: PyPI praisonai >=0 <=4.5.114)

Commands are suggestions: review each one before running it.