gitlab-automation

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the configuration of an external Model Context Protocol (MCP) server at https://rube.app/mcp. This endpoint provides the toolkit necessary for GitLab automation and is a core part of the skill's intended functionality.
  • [COMMAND_EXECUTION]: The skill documents the use of various tools (e.g., GITLAB_CREATE_PROJECT, GITLAB_UPDATE_PROJECT_ISSUE) to perform administrative and operational tasks on GitLab instances via the connected MCP server.
  • [PROMPT_INJECTION]: As the skill is designed to read and process content from GitLab issues, merge requests, and project descriptions, it has an attack surface for indirect prompt injection from untrusted external data.
  • Ingestion points: Data enters the context through tools like GITLAB_LIST_PROJECT_ISSUES and GITLAB_GET_PROJECT_MERGE_REQUESTS (SKILL.md).
  • Boundary markers: The instructions do not explicitly specify delimiters or safety warnings for the agent to ignore instructions embedded within GitLab content.
  • Capability inventory: The skill has capabilities to create and update projects, issues, and merge requests, as well as manage branches and pipelines.
  • Sanitization: There is no mention of sanitization or validation of the retrieved GitLab data before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 09:19 AM
Security Audit — agent-trust-hub — gitlab-automation