ui-ux-pro-max
Pass
Audited by Gen Agent Trust Hub on Nov 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides a search interface that ingests user-supplied queries to retrieve UI/UX guidelines and code snippets from internal CSV files. This creates a surface for indirect prompt injection where user input influences the context retrieved by the agent.\n
- Ingestion point: The
queryargument passed to thescripts/search.pyscript.\n - Boundary markers: No explicit delimiter or instruction-guarding markers are implemented for the search results.\n
- Capability inventory: The skill is restricted to local file-system read operations on its own data directory. It does not possess network access, file-writing capabilities, or privilege escalation paths.\n
- Sanitization: The
scripts/core.pyscript performs basic sanitization by removing non-alphanumeric characters and converting input to lowercase during tokenization.\n- [SAFE]: The skill's functionality is entirely contained within its provided scripts and local data files. There is no evidence of obfuscation, remote code execution, credential harvesting, or unauthorized data exfiltration. The prerequisite installation instructions inSKILL.mdare standard developer setup procedures.
Audit Metadata