jabraf-dev-setup

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes standard development tasks such as linting, testing, and type-checking using the project's defined package manager. These operations are restricted to validating the newly configured environment and are typical for development tools.
  • [EXTERNAL_DOWNLOADS]: The documentation provides a command for users to install necessary sibling skills from the author's own repository. These references are consistent with the umbrella skill's functionality and the author's namespace.
  • [PROMPT_INJECTION]: The skill reads the project's package.json to automatically determine configuration presets (e.g., React or Node.js settings). While reading external files creates a surface for indirect prompt injection, the risk is mitigated by the skill's flow, which presents a consolidated plan and waits for user approval before proceeding.
  • Ingestion points: package.json (SKILL.md)
  • Boundary markers: Not explicitly defined for the JSON data ingestion.
  • Capability inventory: Local command execution via package managers and npx (SKILL.md).
  • Sanitization: Relies on standard agent processing of structured JSON data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 11:17 AM
Security Audit — agent-trust-hub — jabraf-dev-setup