dev-dashboard

Pass

Audited by Gen Agent Trust Hub on Oct 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill employs Bash scripts to manage the lifecycle of a local web server.
  • start.sh uses nohup node to launch the dashboard server as a background process, ensuring it persists independently of the agent session.
  • stop.sh uses pgrep and kill to safely terminate server instances by matching the specific file path of the bundled entry point.
  • [INDIRECT_PROMPT_INJECTION]: The dashboard acts as a viewer for local project files, which constitutes a potential injection surface if an agent is directed to read the dashboard's output.
  • Ingestion points: The frontend application (index-BXvuNVOi.js) fetches data from local API endpoints that scan project directories for status, decisions, and blockers.
  • Capability inventory: The skill has permission to execute shell commands and run a local Node.js server.
  • Sanitization: While the client uses a markdown parser for rendering, the display of arbitrary text from local project files is a standard indirect injection vector common to documentation and dashboard tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 14, 2026, 03:34 AM