Vulnerability · Published Oct 23, 2026 · Assigned by GitHub_M
CVE-2026-56840PraisonAI: HTTPApproval dashboard renders tool arguments as raw HTML, allowing approval-page XSS to approve dangerous tools
High 8.8
In plain English
A high-severity cross-site scripting in PraisonAI from MervinPraison. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.4% (higher than 32% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.
Official description
PraisonAI is a multi-agent teams system. From version 4.5.2 to before version 4.6.59, praisonai.bots.HTTPApproval renders pending tool approval arguments directly into the approval dashboard HTML. An attacker-controlled tool argument can inject JavaScript into that page. When a human opens the approval URL to inspect the risky tool request, the script runs in the dashboard origin and can POST to the same request's /approve/{request_id}/decide endpoint, causing HTTPApproval to return approved=True. This issue has been patched in version 4.6.59.
Affected packages & fixed versions
| Ecosystem | Package | Fixed in | Advisory |
|---|---|---|---|
| PyPI | praisonai | 4.6.59 | GHSA-63v4-w882-g4x2 |
| PyPI | praisonai | 4.6.59 | PYSEC-2026-3503 |
Affected products (as reported)
| Vendor | Product | Versions |
|---|---|---|
| MervinPraison | PraisonAI | >= 4.5.2, < 4.6.59 |
Weakness: CWE-79 · Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H