Skills
Navigate
skills/g1joshi/agent-skills/gitlab/Gen Agent Trust Hub

gitlab

Pass

Audited by Gen Agent Trust Hub on Oct 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to manage GitLab resources like Merge Requests and Issue boards, creating a surface for indirect prompt injection where malicious instructions embedded in external project content could attempt to influence the agent.
  • Ingestion points: GitLab Merge Request descriptions, issue comments, and repository metadata (SKILL.md).
  • Boundary markers: None identified in the provided instructions.
  • Capability inventory: Shell command execution via glab CLI and GitLab REST API interaction using curl.
  • Sanitization: Not explicitly detailed in the instructional content.
  • [EXTERNAL_DOWNLOADS]: The skill references the official GitLab CLI repository on GitLab for documentation and tooling purposes. References to well-known service providers for their official tools are considered safe and routine practice.
  • Evidence: Reference link to https://gitlab.com/gitlab-org/cli in SKILL.md.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 11, 2026, 03:36 AM