product-ui-audit
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill functions by analyzing untrusted external data such as live web pages, screenshots, and code repositories. This behavior introduces a surface for indirect prompt injection attacks.
- Ingestion points: SKILL.md (Instructions to inspect screenshots, live pages, and repository contents).
- Boundary markers: The instructions do not define delimiters or specific warnings to ignore instructions found within the audited content.
- Capability inventory: The skill is limited to analysis and reporting; it includes an explicit instruction to not edit code or design files, which significantly reduces the potential impact of an injection.
- Sanitization: No sanitization or filtering logic is provided for the ingested data.
- [NO_CODE]: The skill consists entirely of markdown-based instructions and YAML configuration. It does not include, download, or execute any Python, Node.js, or shell scripts.
Audit Metadata