SuperAGI Output Handler eval() RCE (CVE-2024-21552) - ATR-2026-00432 (cc1b6b50-ef22-5828-9b8c-edf7e6f7d3ee)

Detects exploitation of CVE-2024-21552 (CVSS 9.8), arbitrary code execution in all versions of SuperAGI. The vulnerable sink is eval() in superagi/agent/output_handler.py (lines 149 and 180); attacker induces the LLM to emit Python code in a position where output_handler subsequently passes it to eval(), gaining unauthenticated RCE on the SuperAGI host. This rule detects the LLM-output payload patterns that reach that sink: Python interpreter calls combined with process-spawning or filesystem APIs inside content fields a SuperAGI agent is likely to evaluate. CWE-94.

Cluster A	Galaxy A	Cluster B	Galaxy B	Level
LLM Prompt Injection (19cd2d12-66ff-487c-a05c-e058b027efc9)	MITRE ATLAS Attack Pattern	SuperAGI Output Handler eval() RCE (CVE-2024-21552) - ATR-2026-00432 (cc1b6b50-ef22-5828-9b8c-edf7e6f7d3ee)	Agent Threat Rules	1
SuperAGI Output Handler eval() RCE (CVE-2024-21552) - ATR-2026-00432 (cc1b6b50-ef22-5828-9b8c-edf7e6f7d3ee)	Agent Threat Rules	Python - T1059.006 (cc3502b5-30cc-4473-ad48-42d51a6ef6d1)	Attack Pattern	1
SuperAGI Output Handler eval() RCE (CVE-2024-21552) - ATR-2026-00432 (cc1b6b50-ef22-5828-9b8c-edf7e6f7d3ee)	Agent Threat Rules	Command and Scripting Interpreter - T1059 (7385dfaf-6886-4229-9ecd-6fd678040830)	Attack Pattern	1
SuperAGI Output Handler eval() RCE (CVE-2024-21552) - ATR-2026-00432 (cc1b6b50-ef22-5828-9b8c-edf7e6f7d3ee)	Agent Threat Rules	Command and Scripting Interpreter (716d3a6b-2f8c-4a1f-85f7-d884bb7b2800)	MITRE ATLAS Attack Pattern	1
Python - T1059.006 (cc3502b5-30cc-4473-ad48-42d51a6ef6d1)	Attack Pattern	Command and Scripting Interpreter - T1059 (7385dfaf-6886-4229-9ecd-6fd678040830)	Attack Pattern	2