PraisonAI: HTTPApproval dashboard renders tool arguments as raw HTML, allowing approval-page XSS to approve dangerous tools
CVE-2026-56840 · GHSA-63v4-w882-g4x2 · published 2026-06-18 · updated 2026-07-20
- Severity
- High
- CVSS score
- 8.8
- Chance of exploitation (EPSS)
- 0.38%
- Fixed in
- 4.6.59
- Exploitation Public proof of concept
- Automatable No
- Technical impact Total
- CISA SSVC
An attacker who can influence an agent task or prompt enough to produce a dangerous tool call can embed a short XSS payload in the tool argument. When the human approver opens the HTTP approval page, the script can approve the pending dangerous tool call before the human explicitly clicks Approve or Deny. This bypasses the human-in-the-loop approval boundary for dangerous tools such as executecommand, executecode, delete_file, or other tools gated through HTTPApproval. If the agent continues after approval, the dangerous tool runs with the privileges of the PraisonAI process.
Upgrade praisonai to 4.6.59 or later. If you start it from an MCP config with npx or uvx, pin that version so an old cached copy is not used.
Escape every untrusted value before inserting it into the approval HTML: toolname risklevel agent_name every argument key every argument value For example, use html.escape(str(value), quote=True) or a template engine that auto-escapes by default. Add regression tests that include ... in tool arguments and assert that the rendered page contains escaped text, not a script element. Minimal patch shape: Additional hardening: avoid inline JavaScript and add a restrictive Content Security Policy; keep the request id as an unguessable capability, but do not rely on it as an XSS defense; consider requiring a per-request decision token outside attacker-controlled rendered argument fields.
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| praisonai | PyPI | >= 4.5.2, <= 4.6.58 | 4.6.59 |
- CriticalJupyter Server: Stored XSS in `NbconvertFileHandler` / `NbconvertPostHandler` via missing `sandbox` CSPjupyter-server
- CriticalMalicious website can execute commands on the local system through XSS in the OpenCode web UIopencode-ai
- CriticalFlowise is vulnerable to stored XSS via "View Messages" allows credential theft in FlowiseAI admin panelflowise
- CriticalMLFlow Cross-site Scripting vulnerability leads to client-side Remote Code Executionmlflow
- CriticalCross-site Scripting in MLFlowmlflow
- HighAny authenticated user can steal another user's session token via script embedded in a DOCX previewopen-webui
- CriticalPraisonAI: AICoder Arbitrary File Write and Command Execution via LLM Tool Callspraisonai
- CriticalPraisonAI: Code Injection via f-string Interpolation in Deploy API Server Generationpraisonai
- CriticalPraisonAI has a Browser Server WebSocket origin validation bypass via unanchored regex (patch bypass of CVE-2026-40289 / GHSA-8x8f-54wf-vv92praisonai
- CriticalPraisonAI: Arbitrary File Read/Write via `multiedit` Tool Without Path Validationpraisonai
- CriticalPraisonAI: Unauthenticated RCE via Jobs API + Approval Bypasspraisonaiagents, praisonai
- CriticalPraisonAI: AgentOS remains unauthenticated after incomplete fix version and allows remote agent invocationpraisonai
The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.