frontend-design-deslop
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the project directory, creating a surface for potential instruction injection.
- Ingestion points: The procedure in SKILL.md requires reading existing styles, tokens, and brand inputs from the target project.
- Boundary markers: The instructions lack defined delimiters or warnings to ignore commands that might be embedded in the processed style files.
- Capability inventory: The skill is authorized to write multiple files (DESIGN.md, CSS, and token files) and perform commits in the repository as per SKILL.md.
- Sanitization: No sanitization or validation of content from external project files is specified.
Audit Metadata