The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests user health data (weight, activity, and sleep metrics) from the external Withings API, creating a potential surface for malicious instructions if the external data source were compromised.\n
Ingestion points: Data is retrieved from the Withings API host wbsapi.withings.net within the wrapper.js script.\n
Boundary markers: The skill does not implement specific boundary markers or instructions to the agent to distinguish between its own logic and the data fetched from the API.\n
Capability inventory: The skill utilizes the https module for remote data retrieval and the fs module to persist session tokens in a local tokens.json file.\n
Sanitization: No specific sanitization or filtering is applied to the API responses before they are output as JSON for the agent to process.

withings-health