The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could potentially contain embedded instructions intended to influence agent behavior.
Ingestion points: Reads sensitive health information from data/fitness-tracker.json, data/nutrition-tracker.json, and daily logs located in data/health-logs/.
Boundary markers: The skill does not implement boundary markers or instructions to ignore embedded commands within the processed JSON data files.
Capability inventory: The skill is designed for data analysis, trend calculation, and report generation. It does not define subprocess calls, network operations, or file-write capabilities in the analyzed document.
Sanitization: No evidence of data sanitization or validation was found for the external content before it is interpolated into the agent's context.

weightloss-analyzer