gtm-agent
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
spawnandspawnSyncfunctions to execute commands via the GitHub (gh), Vercel (vercel), andgitcommand-line interfaces. These tools are used to manage repositories, create Vercel projects, and configure environment variables as part of the primary deployment purpose. - [DYNAMIC_EXECUTION]: The skill executes internal script files (
setup.mjs,doctor.mjs,slack-live-check.mjs,configure-slack.mjs) using the Node.js runtime to coordinate multi-step deployment and maintenance tasks. - [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it ingests and processes JSON data from Slack App Manifests and repository metadata from the GitHub API. The skill mitigates this by using the data for structured configuration rather than direct instruction execution.
- [EXTERNAL_DOWNLOADS]: The skill clones a repository from the author's GitHub account (
eliasstravik/gtm-agent) to serve as a template for the user's agent deployment.
Audit Metadata