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

glab-security

Pass

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the glab command-line tool to perform security configuration tasks on GitLab projects. These operations are standard uses of the tool and are limited to the scope of GitLab project management.
  • [PROMPT_INJECTION]: The skill processes project identifiers and security profile names which are interpolated into shell commands, representing an indirect prompt injection surface.
  • Ingestion points: Project paths (-R/--repo) and profile names ($PROFILE) in SKILL.md.
  • Boundary markers: None identified.
  • Capability inventory: Subprocess execution of glab for reading and writing project security configurations.
  • Sanitization: No explicit validation or escaping of the interpolated variables is provided.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 20, 2026, 09:15 AM
Security Audit — agent-trust-hub — glab-security