habit-designer
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided descriptions of habits and daily routines, which presents a surface for indirect prompt injection.
- Ingestion points: The skill uses variables
[DESCRIBE THE HABIT],[WHAT MY TYPICAL DAY LOOKS LIKE], and[WHAT I HAVE TRIED BEFORE AND WHY IT FAILED]inSKILL.mdto collect input from the user. - Boundary markers: No specific boundary markers or delimiters (such as XML tags or unique separators) are used to encapsulate the user input, nor are there instructions for the model to ignore instructions contained within that data.
- Capability inventory: The skill contains no executable scripts, tool permissions, file system access, or network capabilities.
- Sanitization: There is no evidence of sanitization, filtering, or validation of the user-provided text before it is interpolated into the prompt template.
Audit Metadata