The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructions and reference materials require the execution of Maven commands such as ./mvnw compile, mvn compile, and mvn clean verify to ensure workspace integrity. These commands are executed in the shell to validate changes to Java build descriptors and database artifacts.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external data including document schemas, collection models, and query pipelines, creating a potential surface for indirect prompt injection. However, the skill provides explicit instructions to sanitize inputs and avoid query concatenation. (1) Ingestion points: The workflow involves reading existing collection schemas and queries from the repository. (2) Boundary markers: None identified. (3) Capability inventory: Shell command execution via Maven and file system read/write access. (4) Sanitization: Explicit instructions in the 'INJECTION' and 'QUERY SAFETY' constraints prohibit string concatenation for queries and require the use of validated parameters.
[SAFE]: The skill demonstrates a strong security posture by including specific safeguards for data safety, bounded document growth, and query injection prevention.

705-technologies-nosql-mongodb