A vulnerability was detected in FoundationAgents MetaGPT up to 0.8.1. This affects the function check_solution of the component HumanEvalBenchmark/MBPPBenchmark. Performing a manipulation results in code injection.
The attack may be initiated remotely. The exploit is now public and may be used. The project was informed of the problem early through a pull request but has not reacted yet.
Attack Parameters
Attack Vector
Network
Can be exploited remotely
Attack Complexity
Low
Easy to exploit
Attack Requirements
None
No additional conditions
Privileges Required
None
No privileges needed
User Interaction
None
No user interaction needed
Impact Assessment
Confidentiality
Low
Partial data leak
Integrity
Low
Partial data modification
Availability
Low
Partial disruption
CVSS Vector v4.0
Weakness Type (CWE)
References 6
https://github.com/FoundationAgents/MetaGPT/
cna@vuldb.com
https://github.com/FoundationAgents/MetaGPT/issues/1942
cna@vuldb.com
https://github.com/FoundationAgents/MetaGPT/pull/1988
cna@vuldb.com
https://vuldb.com/submit/791693
cna@vuldb.com
https://vuldb.com/vuln/356524
cna@vuldb.com
https://vuldb.com/vuln/356524/cti
cna@vuldb.com