execution-gitlab-issue
Pass
Audited by Gen Agent Trust Hub on Jul 24, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it reads and processes untrusted content from external GitLab issues to drive its execution logic. \n
- Ingestion points: In Phase 2, Step 1, the skill uses MCP to read the full payload of a GitLab issue, including the title, description, comments, and attachments. \n
- Boundary markers: The instruction set does not define any boundary markers (such as XML tags or delimiters) or specific instructions to the agent to ignore any embedded commands within the ingested content. \n
- Capability inventory: The skill has significant capabilities, including file system operations (Git worktree management), repository mutations (commits and pushes), and GitLab administrative actions (Merge Request creation and commenting via MCP). It also delegates complex coding tasks to an autonomous execution engine. \n
- Sanitization: No sanitization or validation of the ingested external content is described in the skill's instructions.
Audit Metadata