ddd4j-javalin-extensions
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted project data including Java source code, samples, and build configurations, which presents a risk of embedded instructions influencing agent actions.
- Ingestion points: Local project source code, POM files, and extension samples located in the directory specified in
references/source-evidence.md. - Boundary markers: Absent. The instructions do not provide explicit delimiters or warnings to the agent to ignore instructions found within the ingested source files.
- Capability inventory: The workflow requires the agent to read source files and execute shell commands to "Run composition tests" (Step 4 in
SKILL.md). - Sanitization: Absent. The skill lacks instructions for sanitizing or validating the contents of external code before analysis or test execution.
- [COMMAND_EXECUTION]: The workflow involves running composition tests and exercising entry points, which implies the execution of shell commands on the host environment.
- [EXTERNAL_DOWNLOADS]: The documentation includes instructions to install related skills from the vendor's collection using
npx skills add full-stack-skills/ddd4j-skills.
Audit Metadata