ui-score
Pass
Audited by Gen Agent Trust Hub on Aug 5, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted UI source files to calculate design scores and generate fixes.
- Ingestion points: The skill reads local source files (e.g.,
src/app/Dashboard.tsx) as evidence for its scoring logic. - Boundary markers: There are no explicit instructions to use delimiters or ignore embedded instructions within the processed UI files.
- Capability inventory: In 'Gate mode', the agent is instructed to automatically modify files using referenced tools like
/ss-reviewand re-score them iteratively. - Sanitization: No sanitization of the input file content is mentioned, making it theoretically possible for comments within UI files to influence the scoring process.
Audit Metadata