gitlab
Pass
Audited by Gen Agent Trust Hub on May 6, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface due to the nature of interacting with untrusted GitLab data content.
- Ingestion points: Untrusted data enters the agent context through tools that read GitLab issue descriptions, merge request comments, and raw repository files (e.g.,
glab issue view,glab mr view, andglab api .../repository/files/.../raw). - Boundary markers: No specific delimiters or instructions are provided in the skill to treat the fetched GitLab content as untrusted or to ignore embedded instructions.
- Capability inventory: The skill allows for high-impact actions including merging merge requests (
glab mr merge), approving merge requests (glab mr approve), and modifying issues (glab issue note,glab issue close). - Sanitization: There is no evidence of content sanitization or validation of the fetched external data before processing.
Audit Metadata