The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes data from multiple external sources which represents a potential attack surface.
Ingestion points: The skill reads data from various files including sleep-tracker.json, fitness-tracker.json, mood-tracker.json, and diet records.
Boundary markers: The instructions lack specific delimiters or warnings to the agent to ignore any natural language instructions that might be embedded within these data files.
Capability inventory: The skill is configured to use Read, Grep, Glob, and Write tools. Additionally, it contains Python algorithms intended for execution to perform sleep quality and correlation analysis.
Sanitization: There are no explicit instructions for sanitizing or validating the content of the data files before the agent processes them.

sleep-analyzer