maven-tools
Warn
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
- EXTERNAL_DOWNLOADS (MEDIUM): The skill recommends using an unverified Docker image from an untrusted GitHub user (arvindand/maven-tools-mcp). This involves downloading and running code from an external source not on the trusted list.
- REMOTE_CODE_EXECUTION (MEDIUM): The suggested setup involves 'docker run', which executes the contents of a remote container image. While standard for MCP servers, the lack of a trusted author increases the risk.
- COMMAND_EXECUTION (MEDIUM): The documentation describes executing 'scripts/context7.py' using arguments like library IDs and versions extracted from build files (pom.xml/build.gradle). This creates a vulnerability surface for command injection if the project files contain malicious strings. Ingestion points: Dependency metadata from build files. Boundary markers: None specified. Capability inventory: Execution of local Python scripts and MCP tool calls. Sanitization: Not documented.
Audit Metadata