Trust Assessment
glab-variable 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 Skill grants broad access to GitLab CI/CD variables.
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 | Skill grants broad access to GitLab CI/CD variables The `glab-variable` skill provides the LLM with capabilities to create, update, delete, get, list, and export GitLab CI/CD variables at both project and group levels. These variables often contain sensitive information (e.g., API keys, database credentials) or control critical CI/CD pipeline logic. Granting an LLM direct access to manipulate these variables introduces a significant risk of:
1. **Command Injection/RCE**: An attacker could prompt the LLM to set or update a variable with malicious commands, which could then be executed by a CI/CD pipeline.
2. **Data Exfiltration**: An attacker could prompt the LLM to retrieve or export sensitive variables, leading to the leakage of credentials or other confidential data.
3. **Service Disruption**: An attacker could prompt the LLM to delete or modify critical variables, disrupting CI/CD pipelines or deployed services. To mitigate these risks: * **Restrict LLM access**: Limit the LLM's ability to use this skill, especially in sensitive environments. * **Implement approval workflows**: Require human approval for any variable modification or export operations initiated by the LLM. * **Least privilege**: Configure the underlying GitLab token used by `glab` with the minimum necessary permissions (e.g., read-only access to specific variables, or only for specific projects). * **Input validation/sanitization**: Implement strict validation and sanitization of variable keys and values before they are passed to the `glab` command, especially if the values originate from untrusted user input. * **Monitor activity**: Log and monitor all `glab variable` operations performed by the LLM for suspicious activity. | LLM | SKILL.md:18 |
Scan History
Embed Code
[](https://skillshield.io/report/a93cde33d356cc78)
Powered by SkillShield