Trust Assessment
garmin-skill received a trust score of 100/100, placing it in the Trusted category. This skill has passed all critical security checks and demonstrates strong security practices.
SkillShield's automated analysis identified 1 finding: 0 critical, 0 high, 0 medium, and 0 low severity. Key findings include Broad access to sensitive personal health data.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.
Last analyzed on February 14, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| INFO | Broad access to sensitive personal health data The skill provides the AI agent with broad access to sensitive personal health data from Garmin Connect via the Transition API. This includes activities, training load, VO2 Max, heart rate zones, performance trends, and more. While this is the intended functionality of the skill, it means the AI agent will be able to query and process highly personal and sensitive information. Agents using this skill must be carefully designed and constrained to ensure privacy and prevent misuse or inadvertent exposure of this data. Ensure the AI agent's prompts and internal logic are designed with strong privacy safeguards when interacting with this skill. Implement strict data handling policies and user consent mechanisms for accessing and processing sensitive health data. Consider if granular permissions are available from the API provider to limit access to only strictly necessary data points. | LLM | SKILL.md:39 |
Scan History
Embed Code
[](https://skillshield.io/report/e8cf1c327312bb85)
Powered by SkillShield