The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests data from external sources without sufficient isolation.
Ingestion points: Data is read from files in data/fitness-logs/ and trackers like data/hypertension-tracker.json and data/diabetes-tracker.json.
Boundary markers: Absent; there are no instructions for the agent to distinguish between data and commands within the ingested files.
Capability inventory: The skill uses Read, Grep, Glob, and Write tools for data processing and updates.
Sanitization: Absent; no validation or sanitization of the JSON content is mentioned in the skill definition.

fitness-analyzer