preventing-ui-slop
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided UI briefs, component source code, and design requirements to apply specific constraints.
- Ingestion points: UI task descriptions, component edits, redesign briefs, and UI-generation prompts as specified in SKILL.md.
- Boundary markers: No explicit delimiters or 'ignore embedded instructions' warnings are defined for the data being processed.
- Capability inventory: The skill consists entirely of natural language instructions and does not define any allowed tools or perform actions such as file writes or network requests.
- Sanitization: No sanitization or escaping of the user-provided UI content is described.
- [COMMAND_EXECUTION]: The README.md provides instructions for running local maintenance and validation scripts (scripts/validate.py and scripts/test_skill.py) using Python 3. These scripts perform standard static analysis and unit testing of the skill package components and do not exhibit malicious behavior.
Audit Metadata