design-an-interface
Pass
Audited by Gen Agent Trust Hub on Jul 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect prompt injection surface identified. 1. Ingestion points: [module description] and [gathered requirements] placeholders in SKILL.md. 2. Boundary markers: Absent; user-provided data is not delimited from agent instructions. 3. Capability inventory: Spawns sub-agents via the Task tool for text generation. 4. Sanitization: Absent; external content is interpolated directly into templates.
- [SAFE]: No obfuscation, data exfiltration patterns, or persistence mechanisms were detected in the instructions.
- [SAFE]: The skill does not attempt to download external packages or execute remote code from untrusted sources.
- [SAFE]: No hardcoded credentials or access to sensitive configuration files were found.
Audit Metadata