Trust Assessment
health-guardian received a trust score of 92/100, placing it in the Trusted category. This skill has passed all critical security checks and demonstrates strong security practices.
SkillShield's automated analysis identified 2 findings: 0 critical, 0 high, 1 medium, and 1 low severity. Key findings include Node lockfile missing, Arbitrary File Read via Configured Data Source.
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 | |
|---|---|---|---|---|
| MEDIUM | Arbitrary File Read via Configured Data Source The `import_health.py` script reads the `data_source` path from `config.json` and uses `os.path.expanduser()` to resolve it. This allows the script to access and attempt to parse files or directories at arbitrary locations on the filesystem. If an attacker can manipulate the `config.json` file (e.g., by compromising the agent that writes or modifies the configuration based on untrusted input), they could set `data_source` to sensitive paths like `/etc/passwd`, `/root/.ssh/id_rsa`, or other arbitrary locations. While parsing might fail for non-JSON/ZIP files, the act of opening and reading the file constitutes a data exfiltration risk. Restrict the `data_source` configuration parameter to a specific, sandboxed directory or implement robust path validation to ensure it points only to expected and safe locations. Avoid using `os.path.expanduser()` on potentially untrusted paths. If user input influences `config.json`, ensure strict sanitization and validation of all path-related inputs. | LLM | scripts/import_health.py:150 | |
| LOW | Node lockfile missing package.json is present but no lockfile was found (package-lock.json, pnpm-lock.yaml, or yarn.lock). Commit a lockfile for deterministic dependency resolution. | Dependencies | skills/cgtreadw/health-guardian/package.json |
Scan History
Embed Code
[](https://skillshield.io/report/3799b748e46e6c99)
Powered by SkillShield