The Agent Skills Directory

[DATA_EXPOSURE_AND_EXFILTRATION]: The skill accesses sensitive personal health information located in the data/ directory, including files such as hypertension-tracker.json, diabetes-tracker.json, profile.json, and fitness-tracker.json. While this access is aligned with the skill's stated purpose of fitness and health analysis, the handling of medical data is a sensitive operation.
[INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its processing of external, potentially untrusted data files.
Ingestion points: The skill reads fitness logs and health tracker data from multiple paths: data/fitness-logs/, data/fitness-tracker.json, data/hypertension-tracker.json, and data/diabetes-tracker.json.
Boundary markers: No technical delimiters or instructions to ignore embedded commands within the data were found in the skill's logic.
Capability inventory: The skill utilizes Read, Grep, Glob, and Write tools to process data. No network or remote execution capabilities are present.
Sanitization: There are no instructions provided to sanitize or validate the content of the external files before the agent processes them.

fitness-analyzer