GitHub Repo

Detection: Linux Auditd AI CLI Permission Override Activated

Updated Date: 2026-03-12 ID: 737e8baa-d44e-4fa9-8281-24056ed424c0 Author: Teoderick Contreras, Splunk Type: Anomaly Product: Splunk Enterprise Security

Description

This detection identifies when an AI command-line tool is launched in an unsafe mode that bypasses normal safety checks and user approvals. For instance, running claude --dangerously-skip-permissions skips all safety restrictions, allowing the tool to operate freely, while gemini --yolo automatically approves all actions without prompting the user. These modes, often called permission overrides or YOLO mode, let the AI execute commands, modify files, or perform tasks without confirmation. Detecting their use is important to prevent unintended or potentially harmful operations.

 1`linux_auditd` (proctitle = "*gemini*" AND proctitle IN ("*--yolo*", "*-y *")) OR
 2(proctitle = "*claude*" AND proctitle= "*--dangerously-skip-permissions*")
 3
 4| rename host as dest
 5
 6| stats count min(_time) as firstTime max(_time) as lastTime
 7  BY proctitle dest
 8
 9| `security_content_ctime(firstTime)`
10
11| `security_content_ctime(lastTime)` 
12| `linux_auditd_ai_cli_permission_override_activated_filter`

Data Source

Name Platform Sourcetype Source
Linux Auditd Proctitle Linux icon Linux 'auditd' 'auditd'

Macros Used

Name Value
linux_auditd sourcetype="auditd"
linux_auditd_ai_cli_permission_override_activated_filter search *
linux_auditd_ai_cli_permission_override_activated_filter is an empty macro by default. It allows the user to filter out any results (false positives) without editing the SPL.

Annotations

- MITRE ATT&CK
+ Kill Chain Phases
+ NIST
+ CIS
- Threat Actors
ID Technique Tactic
T1480 Execution Guardrails Defense Evasion
Exploitation
DE.AE
CIS 10

Default Configuration

This detection is configured by default in Splunk Enterprise Security to run with the following settings:

Setting Value
Disabled true
Cron Schedule 0 * * * *
Earliest Time -70m@m
Latest Time -10m@m
Schedule Window auto
Creates Risk Event True
This configuration file applies to all detections of type anomaly. These detections will use Risk Based Alerting.

Implementation

To implement this detection, the process begins by ingesting auditd data, that consist SYSCALL, TYPE, EXECVE and PROCTITLE events, which captures command-line executions and process details on Unix/Linux systems. These logs should be ingested and processed using Splunk Add-on for Unix and Linux (https://splunkbase.splunk.com/app/833), which is essential for correctly parsing and categorizing the data. The next step involves normalizing the field names to match the field names set by the Splunk Common Information Model (CIM) to ensure consistency across different data sources and enhance the efficiency of data modeling. This approach enables effective monitoring and detection of linux endpoints where auditd is deployed

Known False Positives

An administrator or network operator might execute this command legitimately. Please apply the necessary filters to tune that activity.

Associated Analytic Story

Risk Based Analytics (RBA)

Risk Message:

A [$proctitle$] event occurred on host - [$dest$] to bypass AI safety execution with permission override.

Risk Object Risk Object Type Risk Score Threat Objects
dest system 20 No Threat Objects

References

Detection Testing

Test Type Status Dataset Source Sourcetype
Validation ✅ Passing N/A N/A N/A
Unit ✅ Passing Dataset auditd auditd
Integration ✅ Passing Dataset auditd auditd

Replay any dataset to Splunk Enterprise by using our replay.py tool or the UI. Alternatively you can replay a dataset into a Splunk Attack Range

Source: GitHub | Version: 1