cross-platform-mvp-ui-alignment
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of documentation and workflow instructions for UI design auditing. It does not include any scripts, binary files, or automated execution steps. The instructions explicitly mandate the use of synthetic data instead of real tokens or account information, mitigating data exposure risks.\n- [INDIRECT_PROMPT_INJECTION]: The skill identifies a potential attack surface through the ingestion of external repository documentation.\n
- Ingestion points: Processes user-provided specifications, README files, and manifest metadata as described in SKILL.md and references/workflow.md.\n
- Boundary markers: No explicit boundary markers or delimiters for untrusted content are defined.\n
- Capability inventory: The skill's capabilities are restricted to documentation analysis and UI asset generation; it does not have access to tools for system command execution, network operations, or code evaluation.\n
- Sanitization: The workflow includes a requirement to desensitize sensitive fields (tokens, accounts, locations) before they are incorporated into generated assets.
Audit Metadata