glab-runner

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill documents the use of the 'glab' command-line utility for managing GitLab runners. These operations are within the expected scope of a GitLab management tool.
  • [DYNAMIC_EXECUTION]: Includes a Python one-liner ('python3 -c') used as a JSON filter for CLI output. This uses only standard libraries and represents a common, safe pattern for processing command-line data.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests runner metadata from the GitLab API. 1. Ingestion points: 'glab runner list' output. 2. Boundary markers: Not applicable. 3. Capability inventory: 'glab runner delete', 'glab runner update', 'glab runner assign'. 4. Sanitization: Standard JSON parsing is used to extract specific fields.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 07:56 PM
Security Audit — agent-trust-hub — glab-runner