Trust Assessment
gmail-inbox-zero received a trust score of 88/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Potential Command Injection via untrusted email headers.
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 12, 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 | |
|---|---|---|---|---|
| HIGH | Potential Command Injection via untrusted email headers The skill describes executing Python scripts via `subprocess` calls, passing arguments derived from email content, specifically the `<from_header>` for the `filter` action. If the `<from_header>` (an untrusted input) is not properly sanitized or escaped before being passed to a shell command or as arguments to `subprocess.run()`, an attacker could craft a malicious `From:` header to inject arbitrary commands. This could lead to arbitrary code execution on the host system. Implement robust input sanitization and escaping for all arguments passed to `subprocess` calls, especially those derived from untrusted sources like email headers or message IDs. When using `subprocess.run()`, prefer `shell=False` and pass arguments as a list to avoid shell interpretation. Ensure that the `gog_processor.py` script itself correctly handles and escapes these arguments when interacting with the `gog` CLI. | LLM | SKILL.md:89 |
Scan History
Embed Code
[](https://skillshield.io/report/09a840e3b63acbcb)
Powered by SkillShield