PT-2026-59287

A weakness has been identified in FoundationAgents MetaGPT up to 0.8.2. This affects the function Message.check instruct content of the file metagpt/schema.py. Executing a manipulation of the argument mapping can lead to deserialization. The attack is restricted to local execution. The exploit ha...

CVE-2026-11455

A vulnerability was determined in FoundationAgents MetaGPT up to 0.8.2. Affected by this issue is the function checkcmdexists of the file metagpt/utils/common.py. This manipulation of the argument mermaid.path causes command injection. The attack may be initiated remotely. A high degree of...

Arbitrary Command Injection

Overview metagpt is a The Multi-Agent Framework Affected versions of this package are vulnerable to Arbitrary Command Injection in the checkcmdexists function of the file metagpt/utils/common.py when processing the mermaid.path argument. An attacker can execute arbitrary system commands by...

CVE-2026-11455

A vulnerability was determined in FoundationAgents MetaGPT up to 0.8.2. Affected by this issue is the function checkcmdexists of the file metagpt/utils/common.py. This manipulation of the argument mermaid.path causes command injection. The attack may be initiated remotely. A high degree of...

CVE-2026-11455 FoundationAgents MetaGPT common.py check_cmd_exists command injection

A vulnerability was determined in FoundationAgents MetaGPT up to 0.8.2. Affected by this issue is the function checkcmdexists of the file metagpt/utils/common.py. This manipulation of the argument mermaid.path causes command injection. The attack may be initiated remotely. A high degree of...

CVE-2026-11455 FoundationAgents MetaGPT common.py check_cmd_exists command injection

A vulnerability was determined in FoundationAgents MetaGPT up to 0.8.2. Affected by this issue is the function checkcmdexists of the file metagpt/utils/common.py. This manipulation of the argument mermaid.path causes command injection. The attack may be initiated remotely. A high degree of...

EUVD-2026-34985

A vulnerability was determined in FoundationAgents MetaGPT up to 0.8.2. Affected by this issue is the function checkcmdexists of the file metagpt/utils/common.py. This manipulation of the argument mermaid.path causes command injection. The attack may be initiated remotely. A high degree of...

CVE-2026-11455

Summary: CVE-2026-11455 affects FoundationAgents MetaGPT up to 0.8.2. The vulnerability targets the function check_cmd_exists in metagpt/utils/common.py, where manipulating the mermaid.path argument enables a command injection. The issue potentially allows remote initiation with a high attack com...

CVE-2026-11455

A vulnerability was determined in FoundationAgents MetaGPT up to 0.8.2. Affected by this issue is the function checkcmdexists of the file metagpt/utils/common.py. This manipulation of the argument mermaid.path causes command injection. The attack may be initiated remotely. A high degree of...

CVE-2026-11455 FoundationAgents MetaGPT common.py check_cmd_exists command injection

A vulnerability was determined in FoundationAgents MetaGPT up to 0.8.2. Affected by this issue is the function checkcmdexists of the file metagpt/utils/common.py. This manipulation of the argument mermaid.path causes command injection. The attack may be initiated remotely. A high degree of...

PT-2026-47177

Name of the Vulnerable Software and Affected Versions FoundationAgents MetaGPT versions prior to 0.8.3 Description Command injection is possible via the mermaid.path argument in the check cmd exists function located in the metagpt/utils/common.py file. This issue allows a remote attacker to execu...

MetaGPT 命令注入漏洞

MetaGPT is a multi-agent framework developed by MetaGPT Inc. Versions of MetaGPT 0.8.2 and earlier contained a command injection vulnerability. This vulnerability stemmed from the erroneous handling of the parameter mermaid.path in the function checkcmdexists found in the file...

CVE-2026-10566

A weakness has been identified in FoundationAgents MetaGPT up to 0.8.2. This affects the function Message.checkinstructcontent of the file metagpt/schema.py. Executing a manipulation of the argument mapping can lead to deserialization. The attack is restricted to local execution. The exploit has...

CVE-2026-5970

A vulnerability was detected in FoundationAgents MetaGPT up to 0.8.1. This affects the function checksolution 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. Th...

CVE-2026-5974

A vulnerability was determined in FoundationAgents MetaGPT up to 0.8.1. The affected element is the function Bash.run in the library metagpt/tools/libs/terminal.py. This manipulation causes os command injection. The attack is possible to be carried out remotely. The project was informed of the...

FoundationAgents MetaGPT: Deserialization through flawed argument mapping via Message.check_instruct_content()

A weakness has been identified in FoundationAgents MetaGPT up to 0.8.2. This affects the function Message.checkinstructcontent of the file metagpt/schema.py. Executing a manipulation of the argument mapping can lead to deserialization. The attack is restricted to local execution. The exploit has...

GHSA-3C3G-7HWG-9QMR FoundationAgents MetaGPT: Deserialization through flawed argument mapping via Message.check_instruct_content()

A weakness has been identified in FoundationAgents MetaGPT up to 0.8.2. This affects the function Message.checkinstructcontent of the file metagpt/schema.py. Executing a manipulation of the argument mapping can lead to deserialization. The attack is restricted to local execution. The exploit has...

CVE-2026-10566

A weakness has been identified in FoundationAgents MetaGPT up to 0.8.2. This affects the function Message.checkinstructcontent of the file metagpt/schema.py. Executing a manipulation of the argument mapping can lead to deserialization. The attack is restricted to local execution. The exploit has...

Deserialization of Untrusted Data

Overview metagpt is a The Multi-Agent Framework Affected versions of this package are vulnerable to Deserialization of Untrusted Data via the Message.checkinstructcontent function in metagpt/schema.py. An attacker can execute arbitrary code by providing specially crafted input to the argument...

CVE-2026-10566 FoundationAgents MetaGPT schema.py Message.check_instruct_content deserialization

A weakness has been identified in FoundationAgents MetaGPT up to 0.8.2. This affects the function Message.checkinstructcontent of the file metagpt/schema.py. Executing a manipulation of the argument mapping can lead to deserialization. The attack is restricted to local execution. The exploit has...