Fubuki8087

**Name of the Vulnerable Software and Affected Versions** MetaGPT versions 0.6.4 and earlier **Description** The issue allows the QaEngineer role to execute arbitrary code because `RunCode.run script()` passes shell metacharacters to `subprocess.Popen`. This enables potential exploitation, but specific details about the number of affected devices or real-world incidents are not provided. **Recommendations** For MetaGPT versions 0.6.4 and earlier, as a temporary workaround, consider restricting the `QaEngineer` role's access to the `RunCode.run script()` function until a patch is available. Additionally, avoid passing user-controlled input to `subprocess.Popen` to minimize the risk of exploitation. At the moment, there is no information about a newer version that contains a fix for this issue.

**Name of the Vulnerable Software and Affected Versions** LlamaIndex (aka llama index) versions 0.9.34 and earlier **Description** The issue allows SQL injection via the Text-to-SQL feature in NLSQLTableQueryEngine, SQLTableRetrieverQueryEngine, NLSQLRetriever, RetrieverQueryEngine, and PGVectorSQLQueryEngine. For example, an attacker might be able to delete this year's student records via "Drop the Students table" within English language input. **Recommendations** For versions 0.9.34 and earlier, consider disabling the Text-to-SQL feature in the affected engines until a patch is available. Restrict access to the NLSQLTableQueryEngine, SQLTableRetrieverQueryEngine, NLSQLRetriever, RetrieverQueryEngine, and PGVectorSQLQueryEngine to minimize the risk of exploitation. Avoid using the Text-to-SQL feature with untrusted input until the issue is resolved. At the moment, there is no information about a newer version that contains a fix for this vulnerability.

**Name of the Vulnerable Software and Affected Versions** PandasAI (aka pandas-ai) versions 1.5.17 and earlier **Description** The issue allows attackers to trigger the generation of arbitrary Python code that is executed by SDFCodeExecutor. An attacker can create a dataframe that provides an English language specification of this Python code. This is possible due to a flaw in the GenerateSDFPipeline in synthetic dataframe. **Recommendations** For versions 1.5.17 and earlier, as a temporary workaround, consider disabling the `GenerateSDFPipeline` function in `synthetic dataframe` until a patch is available. At the moment, there is no information about a newer version that contains a fix for this vulnerability.