avalonia-layout-zafiro
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill includes a 'Selective Reading Rule' in SKILL.md which acts as a behavioral constraint for the agent. While intended for efficiency, it is an instruction that overrides default behavior.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface through its reliance on external data.
- Ingestion points: SKILL.md instructs the agent to reference an external implementation located at /mnt/fast/Repos/angor/src/Angor/Avalonia/Angor.Avalonia.sln.
- Boundary markers: Absent. There are no instructions or delimiters defining how to handle content from the external repository safely.
- Capability inventory: The skill has access to Read, Write, Edit, Glob, and Grep tools, allowing significant modification of the environment based on ingested content.
- Sanitization: Absent. No validation or sanitization of the external repository's contents is performed.
- [SAFE]: No hardcoded credentials, malicious scripts, or unauthorized network activity were detected in the provided skill files.
Audit Metadata