The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted data from several local JSON files during its analysis workflow. Ingestion points: As described in Step 2, the skill reads data from data/family-health-tracker.json, data/hypertension-tracker.json, data/diabetes-tracker.json, and data/profile.json. Boundary markers: The instructions do not define any delimiters or provide specific warnings to the agent to disregard instructions that might be embedded within the health data files. Capability inventory: The skill uses the Read, Write, Grep, and Glob tools to handle data and generate reports. Sanitization: There are no mentioned validation or sanitization routines for the content retrieved from the JSON files before it is processed or interpolated into the final reports.

family-health-analyzer