setup-dev
Pass
Audited by Gen Agent Trust Hub on Mar 20, 2026
Risk Level: SAFEREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONCREDENTIALS_UNSAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill downloads and executes shell scripts from external repositories to facilitate installation.\n
- Fetches the Homebrew installation script from the official Homebrew GitHub repository.\n
- Downloads the
devenvinstallation script from the getsentry GitHub repository and pipes it directly to bash for execution.\n- [COMMAND_EXECUTION]: The skill performs various system configuration and application management commands.\n - Uses
xcode-select,brew, anddockerto manage system prerequisites and services.\n - Directly modifies shell configuration files (
.zshrc,.bashrc) to update the systemPATHand initialize environment hooks fordirenv.\n - Executes
devenvanddevservicescommands for environment synchronization and service orchestration.\n - Runs Sentry CLI tools to perform database migrations and initialize local application data.\n- [CREDENTIALS_UNSAFE]: The skill provides instructions for creating a local administrative user with a predefined password.\n
- The command
.venv/bin/sentry createuserincludes the hardcoded passwordadminfor initial setup in local development environments.\n- [EXTERNAL_DOWNLOADS]: The skill initiates the download of several software packages and service images.\n - Pulls multiple Docker images for services including PostgreSQL, Redis, Kafka, and ClickHouse as part of the application infrastructure setup.\n- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface through its use of external documentation tools.\n
- Ingestion points: The
al_read_doctool inSKILL.mdreads content from thegetsentry/devinfra-mcpdocumentation repository.\n - Boundary markers: Absent; there are no specified delimiters to separate external documentation content from agent instructions.\n
- Capability inventory: The skill has extensive capabilities to execute shell commands and modify system configuration files.\n
- Sanitization: Absent; the skill does not explicitly describe validation or sanitization of content retrieved from documentation repositories.
Audit Metadata