Advisory

PYSEC-2026-3896

Details, part 2 of 2. The advisory

Details

"todo_response_text": todo.json().get("result", {}).get("content", [{}])[0].get("text"),
"todo_file_exists": todo_file.exists(),
}, indent=2))


Observed output:

```json
{
  "blocked_origin_status": 403,
  "bypass_origin_status": 200,
  "bypass_response_text": "File created: file-safe-local-poc",
  "captured_file_basename": "safe-marker.txt",
  "captured_file_content": "SAFE_LOCAL_MARKER_MCP_FILE_READ",
  "todo_status": 200,
  "todo_response_text": "Todo added: 0440613d",
  "todo_file_exists": true
}

The important results are:

  • Origin: https://evil.example is rejected with 403.
  • Origin: http://localhost.evil.example is accepted with 200.
  • The bypassed request invokes praisonai.files.create and reads the local safe marker file.
  • The bypassed request invokes praisonai.todo.add and writes local PraisonAI state.

Impact

A malicious webpage can bypass the localhost Origin allowlist and trigger MCP tools/call requests against a locally running unauthenticated HTTP Stream server.

In local testing, this allowed invoking registered PraisonAI tools that:

  • read an attacker-selected local file path and pass the file handle to the configured LiteLLM provider; and
  • modify local PraisonAI state by writing to ~/.praison/todo.json.

The default MCP HTTP Stream bind address is localhost, so exploitation is browser-mediated. A practical attack requires the victim to run the HTTP Stream MCP server without an API key and visit an attacker-controlled origin that matches the prefix bypass, or a DNS-rebinding-style setup. If an API key is configured, exploitability is significantly reduced.

Sources & licences