The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to how it handles data persistence and retrieval.
Ingestion points: The skill ingests natural language from users to populate fields such as note in teeth_status, description in treatment_records, and description in oral_issues within the data/oral-health-tracker.json file.
Boundary markers: No specific boundary markers or delimiters are defined in the instructions to isolate user-provided data from agent instructions when the data is read back during status, trend, or reminder operations.
Capability inventory: The skill utilizes Read and Write tools to manage the data/oral-health-tracker.json file as defined in the SKILL.md frontmatter.
Sanitization: There is no evidence of sanitization or validation logic to filter out potential instructions embedded within the user-provided dental notes.

oral-health