Trust Assessment
glab-milestone 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 --repo flag.
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 --repo flag The skill describes the `glab milestone` command, which includes a `--repo` flag. This flag explicitly accepts a 'full URL or Git URL'. If an LLM constructs a `glab` command using unsanitized user input for the `--repo` flag, a malicious URL containing shell metacharacters (e.g., `https://example.com/repo; rm -rf /`) could lead to command injection. The LLM's execution environment or the `glab` tool itself must properly sanitize or escape this input to prevent arbitrary command execution. Implement robust input validation and sanitization for any user-provided input used to construct the `--repo` argument. Ensure that shell metacharacters are properly escaped or quoted before executing the `glab` command. The LLM should be instructed to treat all user input for this flag as untrusted and escape it appropriately. | LLM | SKILL.md:20 |
Scan History
Embed Code
[](https://skillshield.io/report/119643a6fea674cc)
Powered by SkillShield