Trust Assessment
strava received a trust score of 94/100, 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, 1 medium, and 0 low severity. Key findings include Exposure of sensitive tokens via stdout.
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 13, 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 | |
|---|---|---|---|---|
| MEDIUM | Exposure of sensitive tokens via stdout The `refresh_token.sh` script explicitly prints the newly acquired `access_token` and `refresh_token` to standard output. In an automated agent environment, this output can be captured by logs or other processes, potentially exposing sensitive credentials. While the skill's documentation suggests manual user update, an agent executing this script might inadvertently expose these tokens. Avoid printing sensitive credentials directly to stdout. Instead, consider mechanisms for secure credential storage (e.g., updating a secure configuration file directly, or returning tokens via a secure channel if the agent is designed to handle them programmatically). If printing is necessary for user interaction, implement masking or clear warnings about sensitive data. | LLM | scripts/refresh_token.sh:22 |
Scan History
Embed Code
[](https://skillshield.io/report/8aa92cc7198a0dcf)
Powered by SkillShield