zephyr-integration
Pass
Audited by Gen Agent Trust Hub on Jul 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns were detected. The skill is designed for debugging Zephyr RTOS.
- [PROMPT_INJECTION]: The skill ingests untrusted data which presents a surface for indirect prompt injection.
- Ingestion points: User-provided prj.conf, devicetree overlays, and west build logs (SKILL.md).
- Boundary markers: None defined in the instructions.
- Capability inventory: No file-writing, network communication, or shell command execution capabilities are present in the skill.
- Sanitization: No validation or sanitization of the ingested configuration files is performed.
Audit Metadata