The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the processing of external data files.
Ingestion points: Data is read from data/travel-health-tracker.json and data-example/travel-health-tracker.json to generate reports and emergency cards.
Boundary markers: The instructions do not define clear delimiters or include warnings to ignore instructions embedded within the health data fields.
Capability inventory: The skill has Write access to the local filesystem, which could be abused if malicious instructions are processed from the input data.
Sanitization: There is no evidence of sanitization or validation of the data content before it is interpolated into reports or emergency cards.

travel-health-analyzer