gtm-get-started

Pass

Audited by Gen Agent Trust Hub on Oct 7, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill includes a procedure to download and install the author's primary toolset using npx skills add eliasstravik/gtm-skills -g -y if the local environment is missing required components. This represents a functional dependency on the author's own repository.
  • [COMMAND_EXECUTION]: The skill triggers shell-level package management via npx to handle installation of missing skills.
  • [INDIRECT_PROMPT_INJECTION]: The skill reads from potentially user-controlled files to determine the next setup step.
  • Ingestion points: Reads icps/*/ICP.md, personas/*/PERSONA.md, and ../gtm-workspace/references/contract.md.
  • Boundary markers: None observed; the skill reads entire files to detect the presence of data.
  • Capability inventory: Executes shell commands (npx) for installation; however, it delegates all file-writing tasks to the specific sub-skills it invokes.
  • Sanitization: None observed; the skill operates as a high-level orchestrator.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 7, 2026, 01:11 PM