gitlab-automation
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill relies on an external MCP server hosted at
https://rube.app/mcpto provide its automation tools. Users are instructed to add this endpoint to their client configuration. - [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection attacks by processing external data and having powerful write capabilities.
- Ingestion points: Untrusted data enters the agent context via GitLab tools such as
GITLAB_LIST_PROJECT_ISSUES,GITLAB_GET_PROJECT_MERGE_REQUESTS, andGITLAB_LIST_REPOSITORY_COMMITS(SKILL.md). - Boundary markers: The instructions do not define boundary markers or delimiters to help the agent distinguish between its instructions and the data retrieved from GitLab.
- Capability inventory: The skill includes extensive capabilities to modify the GitLab environment, including
GITLAB_CREATE_PROJECT_ISSUE,GITLAB_UPDATE_PROJECT_ISSUE,GITLAB_CREATE_REPOSITORY_BRANCH, andGITLAB_CREATE_PROJECT(SKILL.md). - Sanitization: There is no mention of sanitizing or validating the content retrieved from GitLab before the agent acts upon it.
Audit Metadata