skills/mem0ai/mem0/switch-project/Gen Agent Trust Hub

switch-project

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the bash tool to execute Python code that reads and modifies configuration files located at ~/.mem0/settings.json and ~/.mem0/project_map.json.
  • [COMMAND_EXECUTION]: The skill interpolates user-provided project names into a Python script string. While this creates a potential code injection surface if the input is not sanitized by the agent, the behavior is intended for local configuration management of the mem0 service and does not involve network exfiltration or privilege escalation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 04:11 PM
Security Audit — agent-trust-hub — switch-project