spring-data-jdbc
Pass
Audited by Gen Agent Trust Hub on Jul 7, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes project source code (Java and Kotlin files) to detect existing architectural patterns and naming conventions. While this involves ingesting untrusted data, the skill does not expose dangerous capabilities like network access or arbitrary shell execution of the ingested content. The agent is instructed to use structured delimiters when interacting with developers, reducing the risk of instructions in the code being misinterpreted as system commands.
- [COMMAND_EXECUTION]: The skill uses
rg(ripgrep) as a fallback mechanism to locate specific annotations and class definitions within the local project directory. These search operations are restricted to finding static patterns and do not involve executing file content or utilizing user-provided arguments in a shell context. - [EXTERNAL_DOWNLOADS]: The skill references an
amplicode-installskill to facilitate the setup of the Amplicode IntelliJ plugin and MCP server. This is a standard vendor-provided installation workflow required for the skill's primary functionality and does not involve downloading code from untrusted or unknown sources.
Audit Metadata