skills/clawdbot/skills/dexcom/Gen Agent Trust Hub

dexcom

Pass

Audited by Gen Agent Trust Hub on Feb 22, 2026

Risk Level: SAFE
Full Analysis
  • [CREDENTIALS_SAFE] (SAFE): The skill handles sensitive Dexcom credentials using environment variables (DEXCOM_USER, DEXCOM_PASSWORD) as recommended, avoiding hardcoded secrets.
  • [EXTERNAL_DOWNLOADS] (SAFE): The skill utilizes the pydexcom and fire Python packages. These are standard libraries for this use case and are managed through the uv package manager.
  • [DATA_EXFILTRATION] (SAFE): Network activity is restricted to communicating with the official Dexcom Share API to retrieve glucose data. No unauthorized data transmission to third-party servers was found.
  • [COMMAND_EXECUTION] (SAFE): The script does not utilize unsafe subprocess calls or evaluate arbitrary strings as code.
  • [INDIRECT_PROMPT_INJECTION] (SAFE): While the skill processes data from an external API (Dexcom), it does not use this data to construct LLM prompts or execute system commands, effectively nullifying the risk of indirect injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 22, 2026, 06:45 PM
Security Audit — agent-trust-hub — dexcom