CVE-2026-47396 Google Chronicle · YARA-L

Detect PraisonAI Call Server Unauthenticated Agent Access (CVE-2026-47396) in Google Chronicle

Detects exploitation of CVE-2026-47396, a critical authentication bypass in PraisonAI's call server component. When the CALL_SERVER_TOKEN environment variable is unset, the server exposes unauthenticated endpoints for listing, invoking, and deleting AI agents. An attacker can enumerate available agents, invoke arbitrary agent workflows, or destroy agent configurations without any credentials. CVSS 9.8 (Critical), CWE-284/CWE-306.

MITRE ATT&CK

Tactic
Initial Access Persistence Impact

YARA-L Detection Query

Google Chronicle (YARA-L)
yaral
rule cve_2026_47396_praisonai_unauth_agent_access {
  meta:
    author = "df00tech"
    description = "Detects unauthenticated access to PraisonAI call server agent endpoints (CVE-2026-47396)"
    severity = "CRITICAL"
    priority = "HIGH"
    reference = "https://github.com/advisories/GHSA-86qc-r5v2-v6x6"

  events:
    $e.metadata.event_type = "NETWORK_HTTP"
    $e.network.http.method in ["GET", "POST", "DELETE"]
    re.regex($e.network.http.target_url, `/agents|/invoke|/delete`)
    not re.regex($e.network.http.request_headers["authorization"], `(?i)bearer .+`)
    $ip = $e.principal.ip

  match:
    $ip over 5m

  condition:
    #e > 2
}
critical severity medium confidence

Chronicle YARA-L rule detecting multiple unauthenticated HTTP requests to PraisonAI call server agent, invoke, or delete endpoints within a 5-minute window from the same source IP.

Data Sources

Chronicle UDM network eventsWeb proxy logs ingested to ChronicleGoogle Cloud Armor logs

Required Tables

chronicle_udm_events

False Positives & Tuning

  • Monitoring agents hitting agent endpoints without configured tokens
  • Development/staging environments with auth intentionally disabled
  • API testing tools without credential configuration
  • Internal service accounts with header propagation issues

Other platforms for CVE-2026-47396


Testing Methodology

Validate this detection against 4 adversary techniques from Atomic Red Team. Each test below lists the behaviour to exercise and the telemetry you should expect to see. Executable commands and cleanup steps are available with Pro.

  1. Test 1Enumerate PraisonAI agents without authentication

    Expected signal: Web server access log entry: GET /agents HTTP/1.1 from test source IP, no Authorization header, HTTP 200 response with JSON agent listing

  2. Test 2Invoke PraisonAI agent without authentication

    Expected signal: Web server access log entry: POST /invoke HTTP/1.1 from test source IP, no Authorization header, HTTP 200 or 202 response; application log showing agent invocation

  3. Test 3Delete PraisonAI agent configuration without authentication

    Expected signal: Web server access log entry: DELETE /delete HTTP/1.1 from test source IP, no Authorization header; application log showing agent deletion event

  4. Test 4Confirm CALL_SERVER_TOKEN absence in running process

    Expected signal: Process environment read via /proc/<pid>/environ; output contains no CALL_SERVER_TOKEN entry

Unlock Pro Content

Get the full detection package for CVE-2026-47396 including response playbook, investigation guide, and atomic red team tests.

Response PlaybookInvestigation GuideHunting QueriesAtomic Red Team TestsTuning Guidance

Related Detections