ddd4j-cloud-tenant
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONMETADATA_POISONING
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external data such as POM files, source code, and project metadata to verify tenant isolation logic. This creates a potential surface for indirect prompt injection if the analyzed files contain malicious instructions.
- Ingestion points: Source code, POM files, and CodeGraph evidence (referenced in
references/source-evidence.md). - Boundary markers: The skill does not define specific delimiters or warnings to ignore embedded instructions in the data it processes.
- Capability inventory: Includes analyzing SQL filtering exemptions, reviewing ignore rules, and tracing cross-service propagation.
- Sanitization: No explicit sanitization or filtering of external content is mentioned.
- [METADATA_POISONING]: The file
references/source-evidence.mdcontains a hardcoded local file path (/Users/wandl/workspaces/workspace-ddd4j/workspace-ddd4j-cloud/ddd4j-cloud). While likely a developer artifact, it exposes specific environment metadata from the author's system.
Audit Metadata