MCP Prompt Injection
This detection identifies potential prompt injection attempts within MCP (Model Context Protocol) communications by monitoring for known malicious phrases and patterns commonly used to manipulate AI assistants.…
Description
This detection identifies potential prompt injection attempts within MCP (Model Context Protocol) communications by monitoring for known malicious phrases and patterns commonly used to manipulate AI assistants. Prompt injection is a critical vulnerability where adversaries embed hidden instructions in content processed by AI tools, attempting to override system prompts, bypass security controls, or hijack the AI's behavior. The search monitors JSON-RPC traffic for phrases such as "IGNORE PREVIOUS INSTRUCTIONS," "SYSTEM PROMPT OVERRIDE," and "ignore all security" which indicate attempts to subvert the AI's intended behavior and potentially execute unauthorized actions through the MCP toolchain.
Detection logic
Detection requirements
- Platform
- ContainersESXiIaaSIdentity ProviderLinuxmacOSNetwork DevicesOffice SuiteSaaSWindows
The rule states no platform. This is derived from the ATT&CK technique it maps to.
- Log source category
- mcp_server
Known benign triggers
- Known false positives include security research and testing activities where red teams or developers intentionally test prompt injection defenses, as well as educational content where documentation, tutorials, or training materials discussing prompt injection techniques are legitimately processed by the AI assistant. Additionally, security tool development involving code reviews or development of prompt injection detection mechanisms may contain these patterns, and quoted references in conversations where users discuss or report prompt injection attempts they encountered elsewhere could trigger this detection.
MITRE ATT&CK mappings
0 exclusive techniques.This is coverage no other published rule has; it is not this rule's total technique count.
References
| Reference | Cited by |
|---|---|
| splunkbase.splunk.com/app/8377 | 5 |
| www.splunk.com/en_us/blog/security/securing-ai-agents-model-context-protocol.html | 5 |
| www.tenable.com/blog/mcp-prompt-injection-not-just-for-evil | Only this detection cites it |
From the source
- At source
- Open at source
- Upstream identifier
- 49779398-b738-4d64-bb3f-ead6eb97fe53
- Tagged by the source as
- Suspicious MCP ActivitiesWeb ApplicationapplicationSplunk CloudSplunk EnterpriseSplunk Enterprise Securityendpoint
Licence
- Published under
- Apache License 2.0Read the licence
- Attribution
- Required
- Obtained under
- Apache-2.0Read the origin licence
Authorship
- Written by
- Published
- Aug 26, 2026
- Version
- 1