Skills
skills/vince-winkintel/gitlab-cli-skills/glab-job/Gen Agent Trust Hub

glab-job

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill recognizes the risk of indirect prompt injection from untrusted GitLab content (job logs, commit messages). It includes proactive security warnings in SKILL.md and explicit boundary markers in scripts/ci-debug.sh to instruct the agent to treat fetched content as data only and ignore embedded instructions.
  • [COMMAND_EXECUTION]: The skill executes glab CLI commands and a local bash script (scripts/ci-debug.sh) to view, retry, and debug jobs. These operations are limited to the intended scope of CI/CD job management.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 05:21 AM
Security Audit — agent-trust-hub — glab-job