skills/ninehills/skills/ui-skills/Gen Agent Trust Hub

ui-skills

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOWPROMPT_INJECTION
Full Analysis
  • [Prompt Injection] (LOW): The skill contains an indirect prompt injection surface through its file review functionality.
  • Ingestion points: The /ui-skills <file> command processes untrusted external data provided in file format.
  • Boundary markers: The instructions do not specify any delimiters or safety constraints to prevent the agent from obeying instructions embedded within the reviewed files.
  • Capability inventory: The skill's primary capability is generating text-based code reviews and code suggestions; it does not have direct write access to the filesystem or execution capabilities.
  • Sanitization: No sanitization or filtering of the input file content is implemented.
  • [Safe] (INFO): No evidence of hardcoded credentials, data exfiltration, obfuscation, or persistence mechanisms was found. The skill operates within the context of UI design guidance.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 11:21 AM