gitlab-cli

Pass

Audited by Gen Agent Trust Hub on Mar 19, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exposes an indirect prompt injection surface by processing data from potentially untrusted external sources.
  • Ingestion points: The agent is instructed to read GitLab issue comments, merge request discussions, and CI/CD trace logs in SKILL.md.
  • Boundary markers: The skill does not define delimiters or specific instructions to treat external GitLab content as non-executable data.
  • Capability inventory: The agent has access to powerful GitLab commands, including merging merge requests, creating/updating issues, and interacting directly with the GitLab REST and GraphQL APIs in SKILL.md.
  • Sanitization: No sanitization or validation mechanisms are described for handling the content retrieved from GitLab.
  • [COMMAND_EXECUTION]: The skill enables the agent to execute a wide variety of GitLab CLI (glab) and API commands, including destructive operations like canceling jobs or making direct API requests to modify project state.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 19, 2026, 09:49 AM