ddd4j-quarkus-data
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze project source code, Maven POM files, and architectural requirements provided by the user, creating a surface where untrusted data enters the agent context.
- Ingestion points: The workflow (SKILL.md) and examples (examples/02-data-layer-review.md) indicate the skill ingests user-provided prompts, project source code, and configuration files.
- Boundary markers: The instructions do not explicitly define boundary markers or delimiters to separate instructions from the data being analyzed.
- Capability inventory: Based on the workflow and examples, the skill's capabilities are limited to analysis, review, and report generation. There are no instructions suggesting the use of network, file-write, or execution tools on user-provided data.
- Sanitization: The skill does not describe specific sanitization or filtering logic for processing external code snippets or configuration values.
Audit Metadata