bulk-data-sharing-design
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of markdown-based instructional content and design guidelines. It does not contain any executable scripts, tool definitions, or automated network operations.
- [DATA_EXFILTRATION]: The instructions explicitly advocate for secure data handling, recommending against proxying data through vendor servers and instead using signed URLs to allow direct, authorized access to object storage. It also prescribes the use of per-recipient credentials and encryption grants to ensure strict tenant isolation.
- [INDIRECT_PROMPT_INJECTION]: While the skill is designed to process user-provided architectural requirements to generate design recommendations, it lacks any executable capabilities (such as shell tools or network clients) that could be exploited by malicious input. The risk of indirect prompt injection affecting the underlying system is negligible.
Audit Metadata