redesign-existing-projects
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves reading and modifying external codebases, which serves as an ingestion point for untrusted data.
- Ingestion points: The 'Scan' instruction in SKILL.md directs the agent to 'Read the codebase'.
- Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following instructions embedded within the scanned code.
- Capability inventory: The skill has the capability to write and modify files during the 'Fix' stage.
- Sanitization: No sanitization or content filtering is implemented for the data ingested during the scan phase.
- [EXTERNAL_DOWNLOADS]: The skill recommends using an external service for generating placeholder images.
- Evidence: https://picsum.photos/seed/{name}/1920/1080 found in SKILL.md under the 'Color and Surfaces' section.
- Context: The skill fetches design assets from a well-known image placeholder service.
Audit Metadata