wellally-tech

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external, untrusted health data formats (XML, ZIP, CSV, JSON) from sources like Apple Health and Fitbit.
  • Ingestion points: Data is ingested through functions such as readAppleHealthExport (SKILL.md), readGenericFile (SKILL.md), and API synchronizations.
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded commands within the ingested data were identified in the skill instructions.
  • Capability inventory: The skill utilizes tool-based file writing (saveToLocalFile) and command-line execution of Python scripts for data processing.
  • Sanitization: The skill documentation mentions basic data validation for types and ranges but lacks specific sanitization for preventing prompt-based attacks within the data payloads.
  • [COMMAND_EXECUTION]: The skill instructions involve executing local Python scripts (e.g., python scripts/import_fitbit.py) to handle data synchronization and parsing tasks.
  • [DATA_EXFILTRATION]: The skill performs network operations to external service APIs (Fitbit, Oura Ring) to synchronize health data and retrieves knowledge base information from wellally.tech.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 07:10 AM
Security Audit — agent-trust-hub — wellally-tech