anti-ui-slop
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill recommends installing content from an external source using a specific command line tool.
- Evidence:
npx skills add https://uizze.com --skill anti-ui-slopin SKILL.md. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external visual references which could potentially contain adversarial instructions aimed at the agent.
- Ingestion points: External data is brought into the agent context via the
find_ui_referencesandfind_ui_materialsMCP tools from the UIZZE service. - Boundary markers: There are no explicit instructions or delimiters provided to ensure the agent ignores text or metadata contained within the retrieved visual evidence.
- Capability inventory: The skill interacts with the local environment by instructing the agent to reuse repository components, render UI results, and inspect them for breakage.
- Sanitization: No sanitization, filtering, or validation steps are defined for the data returned by the external design catalogue.
Audit Metadata