CVE-2026-40111: PraisonAIAgents is a multi-agent teams system. Prior to 1.5.128, he memory hooks executor in praison…
- Occurred
- Apr 9, 2026
- Published
- Apr 9, 2026
- Source
- NVD CVE
Summary
PraisonAIAgents is a multi-agent teams system. Prior to 1.5.128, he memory hooks executor in praisonaiagents passes a user-controlled command string directly to subprocess.run() with shell=True at src/praisonai-agents/praisonaiagents/memory/hooks.py. No sanitization is performed and shell metacharacters are interpreted by /bin/sh before the intended command executes. Two independent attack surfaces exist. The first is via pre_run_command and post_run_command hook event types registered through the hooks configuration. The second and more severe surface is the .praisonai/hooks.json lifecycle configuration, where hooks registered for events such as BEFORE_TOOL and AFTER_TOOL fire automatically during agent operation. An agent that gains file-write access through prompt injection can overwrite .praisonai/hooks.json and have its payload execute silently at every subsequent lifecycle event without further user interaction. This vulnerability is fixed in 1.5.128.
Tags
- CVE
- CVE-2026-40111
- cvss:HIGH
- agent-fail:injection-direct
- agent-fail:injection-indirect
- agent-fail:authorization
- agent-cause:missing-guardrail
- agent-cause:framework-bug
Classification
Rationale: Multi-agent system vulnerability allows command injection via unsanitized user input in lifecycle hooks, enabling silent payload execution.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8