skills/tranz007/ux-skills/frame/Gen Agent Trust Hub

frame

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external documents and data from the .ux/ directory and user-provided research or support evidence.
  • Ingestion points: Files within the .ux/ directory, requirement documents, research data, and support evidence.
  • Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands embedded in the ingested data.
  • Capability inventory: The skill contains no scripts, file-writing logic, or network operations.
  • Sanitization: There are no explicit filtering or sanitization steps for the ingested data.
  • [NO_CODE]: The skill consists entirely of markdown instructions and YAML metadata without any accompanying scripts, binaries, or automated configuration changes.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 02:55 AM
Security Audit — agent-trust-hub — frame