Trust Assessment
github received a trust score of 86/100, 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 for Command Injection and Data Exfiltration via `gh api` and `--jq`.
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 | |
|---|---|---|---|---|
| HIGH | Potential for Command Injection and Data Exfiltration via `gh api` and `--jq` The skill demonstrates the use of the `gh api` command, which allows arbitrary interaction with the GitHub API. If an AI agent constructs this command based on untrusted user input without proper sanitization, it could lead to several security risks. An attacker could craft input to: 1) Exfiltrate sensitive data from private repositories (e.g., `gh api repos/owner/repo/contents/sensitive_file.txt`) if the agent's GitHub token has sufficient permissions. 2) Achieve shell command injection if user-controlled input is not properly escaped when constructing the `gh api` command string. 3) Achieve `jq` program injection via the `--jq` argument, potentially leading to unexpected data manipulation or exposure. The `gh` CLI is a powerful tool, and its `api` subcommand provides broad access, making it a high-risk component if not handled with extreme care. Implement strict input validation and sanitization for any user-provided arguments passed to `gh api` or `--jq`. Consider restricting the specific GitHub API endpoints that the agent can access via `gh api` or using a more granular GitHub token with limited scopes. For `--jq` arguments, ensure user input is properly escaped or only allow a predefined set of safe `jq` filters. Avoid directly interpolating untrusted input into shell commands. | LLM | SKILL.md:30 |
Scan History
Embed Code
[](https://skillshield.io/report/3a570baa113627ee)
Powered by SkillShield