just-design
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from the project workspace, creating a potential surface for indirect prompt injection if those files contain untrusted content.
- Ingestion points: The skill reads
docs/scope-*.mdfiles and repository contents, including screens, components, and design guidance (SKILL.md Step 1 and 2). - Boundary markers: The skill lacks explicit technical delimiters or instructions to ignore embedded commands within the ingested scope documents.
- Capability inventory: The skill has the capability to read repository files and write new design documents to the
docs/directory (SKILL.md Step 7). - Sanitization: There are no explicit instructions to sanitize or escape content retrieved from the scope files before processing or writing the output.
Audit Metadata