The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from multiple health tracking files and uses this information to generate reports and assessments.
Ingestion points: Data is read from data-example/occupational-health-tracker.json, data-example/sleep-tracker.json, data-example/fitness-tracker.json, and data-example/mental-health-tracker.json.
Boundary markers: There are no explicit instructions for the agent to use XML-like tags, delimiters, or specific 'ignore instructions inside data' warnings when processing these files.
Capability inventory: The skill utilizes Read, Grep, Glob, Write, and Edit tools. While it cannot execute arbitrary shell commands, it can modify files based on its analysis.
Sanitization: The instructions do not specify any validation or sanitization steps for the health data content before it is interpolated into the agent's context for risk scoring and report generation.

occupational-health-analyzer