Products / metagpt
metagpt
10 records.
- FoundationAgents MetaGPT: Deserialization through flawed argument mapping via Message.check_instruct_content() Manipulated argument mapping in Message.check_instruct_content leads to unsafe deserialisation of attacker-controlled data during local execution.
- MetaGPT affected by server-side request forgery in metagpt/utils/common.py
- MetaGPT has an eval injection via a cross-site request forgery attack
- MetaGPT has an eval injection in metagpt/strategy/tot.py
- FoundationAgents MetaGPT vulnerable to eval injection Model-generated XML content is passed into eval during ActionNode.xml_fill, so crafted model output causes arbitrary code to run on the server.
- FoundationAgents MetaGPT vulnerable to OS Command Injection in metagpt/tools/libs/terminal.py
- MetaGPT has an Injection issue
- FoundationAgents MetaGPT vulnerable to OS Command Injection in metagpt/utils/common.py
- FoundationAgents MetaGPT vulnerable to os command injection via the Terminal.run_command
- Code execution in metagpt