gitlab-automation

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the processing of untrusted data from GitLab.
  • Ingestion points: External content is fetched from GitLab issues, merge requests, and commit logs via tools such as GITLAB_LIST_PROJECT_ISSUES and GITLAB_GET_PROJECT_MERGE_REQUESTS.
  • Boundary markers: No explicit delimiters or instructions are provided to separate user-controlled content from system prompts.
  • Capability inventory: The skill possesses extensive capabilities to modify the project state, including creating branches (GITLAB_CREATE_REPOSITORY_BRANCH) and updating issues (GITLAB_UPDATE_PROJECT_ISSUE).
  • Sanitization: There is no mention of sanitization or validation for ingested data.
  • [EXTERNAL_DOWNLOADS]: The skill requires the use of an external third-party service provider.
  • Evidence: Users are instructed to add https://rube.app/mcp as an MCP server endpoint to provide the necessary tool functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 09:23 AM