reviewing-data-model
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill instructions and reference materials contain no malicious patterns, obfuscation, or hardcoded credentials.
- [NO_CODE]: The skill consists entirely of Markdown instructions and reference documents; no executable scripts (Python, JS, etc.) are included.
- [PROMPT_INJECTION]: The skill defines its review logic using standard instructional language and does not attempt to bypass safety filters or reveal system prompts.
- [EXTERNAL_DOWNLOADS]: Informational references to well-known industry sources (e.g., AWS, MongoDB, Microsoft) are used neutrally and do not involve automated script execution or untrusted downloads.
- [SAFE]: Indirect Prompt Injection Risk Assessment: (1) Ingestion points: Data-model documents are processed as untrusted input in SKILL.md. (2) Boundary markers: Absent. (3) Capability inventory: No tools are defined for network access, file system writes, or command execution. (4) Sanitization: None. The risk is safe due to the complete lack of exploitable capabilities.
Audit Metadata