gitlab-protected-branch
Pass
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION] (LOW): The skill executes shell commands using the 'glab' CLI to perform branch protection operations. It dynamically constructs commands from user input.
- [Indirect Prompt Injection] (LOW): The skill ingests untrusted data which is interpolated into shell commands. Ingestion points: User-provided project paths and branch names in SKILL.md. Boundary markers: Absent. Capability inventory: Subprocess calls to 'glab' and 'jq' are present in SKILL.md. Sanitization: The skill uses 'jq -Rr @uri' to URL-encode parameters, mitigating simple injection attacks.
- [Dynamic Execution] (LOW): The skill assembles shell command strings from templates at runtime using user variables.
Audit Metadata