sandi
Pass
Audited by Gen Agent Trust Hub on Jul 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown files and reference guides providing software design expertise. No executable scripts, network operations, or sensitive data access patterns were detected. All code snippets provided are static examples for educational purposes.
- [PROMPT_INJECTION]: The skill instructions define clear operational boundaries and personas without attempting to bypass safety filters or override system-level instructions. The use of a custom command (/sandi) is handled through standard instructional logic.
- [DATA_EXFILTRATION]: No network requests or data exfiltration patterns were found. The skill operates locally within the agent's context using provided reference files.
- [SAFE]: The skill's analysis of user-provided code (untrusted data) constitutes a standard interaction surface for a code review tool. While technically an ingestion point, the absence of executable capabilities or tool access within the skill's instructions mitigates the risk of indirect prompt injection.
Audit Metadata