Trust Assessment
fitbit received a trust score of 81/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 2 findings: 0 critical, 1 high, 1 medium, and 0 low severity. Key findings include Potential Command Injection via Unsanitized Date Parameters, Skill Accesses Sensitive Configuration from Root-level Directory.
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 Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Potential Command Injection via Unsanitized Date Parameters The skill defines commands that accept user-provided date parameters (e.g., `daily`, `steps`, `heart`, `sleep`, `activities`). If the AI agent directly interpolates unsanitized user input into these shell commands, a malicious user could inject arbitrary shell commands. For example, providing `2026-02-08; rm -rf /` as a date could lead to arbitrary code execution. This is a common vulnerability when user input is not properly sanitized or quoted before being passed to a shell. Ensure all user-provided arguments passed to shell commands are properly sanitized and quoted. For Python scripts, prefer passing arguments as separate list items to `subprocess.run` (e.g., `['python3', 'script.py', user_input]`) rather than concatenating into a single string, or implement robust input validation and sanitization within the Python script itself. | LLM | SKILL.md:29 | |
| MEDIUM | Skill Accesses Sensitive Configuration from Root-level Directory The skill explicitly states it loads and manages access tokens from `/root/clawd/fitbit-config.json`. Accessing files within the `/root` directory implies that the skill operates with elevated privileges. While this might be necessary for its intended function, broad filesystem access, especially for sensitive credentials, increases the attack surface if the underlying scripts are compromised or contain vulnerabilities. Re-evaluate the necessity of storing configuration files in `/root`. If possible, use a less privileged, dedicated configuration directory for the skill. Ensure strict file permissions on `fitbit-config.json` to prevent unauthorized access. | LLM | SKILL.md:97 |
Scan History
Embed Code
[](https://skillshield.io/report/781fad4ccdc0f86c)
Powered by SkillShield