fitbit-analytics

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local Python scripts (fitbit_api.py, fitbit_briefing.py) to retrieve and analyze fitness data.
  • [DATA_EXFILTRATION]: The skill transmits requests to the well-known Fitbit Web API to fetch user health metrics, which is the core intended functionality.
  • [PROMPT_INJECTION]: The skill ingests external data from the Fitbit API, creating a surface for indirect prompt injection.
  • Ingestion points: Data is pulled from Fitbit API endpoints such as activity summaries and sleep logs.
  • Boundary markers: No specific delimiters are defined to separate ingested data from agent instructions.
  • Capability inventory: The skill has the ability to execute Python scripts based on external data.
  • Sanitization: No evidence of sanitization for API-provided content is present in the skill documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 05:14 AM