fragments-cloud-setup

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the @fragments-sdk/govern package via the project's detected package manager. This is a legitimate vendor resource associated with the skill's author, fragments-sdk.
  • [COMMAND_EXECUTION]: Executes package manager installation commands and the fragments CLI tool to initialize the governance environment and run checks. These operations are restricted to the vendor's own ecosystem.
  • [PROMPT_INJECTION]: The skill analyzes local project metadata to detect frameworks and generate configuration files. While this creates an indirect prompt injection surface, it is standard for development tools.
  • Ingestion points: Reads package.json, lock files (bun, pnpm, yarn, npm), and the project directory structure.
  • Boundary markers: None present for project metadata ingestion.
  • Capability inventory: Performs file writes (.env, fragments.config.ts, .github/workflows/fragments-check.yml, .gitlab-ci.yml) and shell command execution (npm install, npx fragments).
  • Sanitization: No explicit sanitization or validation of local project data before use in configuration generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 05:56 PM