redesign-existing-projects
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill scans untrusted codebase data and has write capabilities, creating a potential surface for instructions embedded in source code comments or strings.
- Ingestion points: The skill reads the existing project codebase to identify frameworks, styling, and design patterns (SKILL.md).
- Boundary markers: The instructions lack explicit delimiters or warnings to treat text within the scanned files as data rather than instructions.
- Capability inventory: The skill enables the agent to read and modify source files across the project (SKILL.md).
- Sanitization: No sanitization or validation of the content read from external files is described.
- [EXTERNAL_DOWNLOADS]: The skill references an external URL for retrieving placeholder assets during the redesign process.
- Reference: The skill suggests fetching images from
https://picsum.photos/seed/{name}/1920/1080(SKILL.md).
Audit Metadata