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

glab-packages

Pass

Audited by Gen Agent Trust Hub on Oct 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the glab CLI tool to interact with GitLab package registries, supporting operations such as listing, uploading, downloading, and deleting packages.
  • [INDIRECT_PROMPT_INJECTION]: The skill interacts with external data by listing packages from GitLab repositories, which constitutes a potential injection surface.
  • Ingestion points: Package metadata is retrieved from the GitLab registry via glab packages list.
  • Boundary markers: The instructions suggest using the --jq flag for structured output in scripts, which helps in properly delimiting data from commands.
  • Capability inventory: The skill can perform file system operations (read for upload, write for download) and network operations (via glab).
  • Sanitization: The skill relies on the glab tool's built-in handling and suggests using jq for robust data processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 27, 2026, 09:10 AM