glab-issue

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from GitLab (issue titles, descriptions, comments) which could be used to influence agent behavior.
  • Ingestion points: issue data is fetched in SKILL.md (via view/list commands) and in scripts/create-mr-from-issue.sh.
  • Boundary markers: The script create-mr-from-issue.sh explicitly marks untrusted content with comments, though broader prompt boundaries are not defined.
  • Capability inventory: The skill uses the glab CLI for API interactions and git for local repository management.
  • Sanitization: The create-mr-from-issue.sh script performs character-level sanitization on issue titles to prevent command injection when creating branches.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 07:07 PM
Security Audit — agent-trust-hub — glab-issue