review-ux-ui

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to process and analyze untrusted content from external sources (URLs via WebFetch or source code via Read/Grep/Glob). This content could contain malicious instructions meant to subvert the agent's logic, known as Indirect Prompt Injection.
  • Ingestion points: The 'Procedure' section requires the agent to ingest external data from a provided URL or prototype source code.
  • Boundary markers: The skill does not include specific delimiters or 'ignore' instructions to prevent the agent from being influenced by text within the analyzed data.
  • Capability inventory: The skill uses retrieval tools (WebFetch) and file system access (Read, Grep, Glob) to gather information for the audit.
  • Sanitization: No sanitization or validation steps are included to filter the incoming data before it is presented to the agent for evaluation.
  • [NO_CODE]: The skill consists entirely of instructional Markdown content and does not include any accompanying scripts (Python, JavaScript, etc.), which reduces the direct execution risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 10:51 PM