The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill's primary workflow involves the ingestion and analysis of external project data, including source code, POM files, and database migrations, to provide configuration and implementation advice.
Ingestion points: The skill targets the project workspace (referenced in references/source-evidence.md) and processes service-specific configuration files and acceptance behaviors.
Boundary markers: The instructions lack specific boundary markers or delimiters to isolate content from analyzed files, which could lead to the agent inadvertently following instructions embedded within the project data.
Capability inventory: The skill possesses the ability to analyze code, diagnose failures, and execute database-related tests, providing a surface for indirect manipulation if the data source is untrusted.
Sanitization: There are no defined procedures for sanitizing or escaping data retrieved from the project environment before it is processed by the agent.
[COMMAND_EXECUTION]: The workflow requires the agent to perform active testing, such as 'Run real database round-trips' and 'Force the failure deliberately' to observe transaction rollbacks. These actions involve executing commands or test suites within the user's development or staging environment.
[EXTERNAL_DOWNLOADS]: The skill suggests the installation of additional capabilities using npx skills add targeting the full-stack-skills/ddd4j-skills repository. These references are for related components provided by the same author to support the ddd4j ecosystem.

ddd4j-cloud-data