jarvus-react

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external data by instructing the agent to fetch library documentation using the context7 MCP server.
  • Ingestion points: The mcp__context7__query-docs tool is used to retrieve content from external repositories (e.g., react-router, tailwindcss) in references/mcp-tools.md.
  • Boundary markers: There are no explicit instructions to delimit or treat the fetched documentation as untrusted data.
  • Capability inventory: The skill context includes the ability to execute shell commands via bun for package installation and project scaffolding, and perform file writes across the src/ directory.
  • Sanitization: No sanitization or validation mechanisms are defined for the content retrieved from external sources.
  • [EXTERNAL_DOWNLOADS]: The skill references several external resources and tools required for the development environment.
  • Downloads the bun runtime manager plugin using asdf plugin add bun in SKILL.md.
  • Utilizes bunx --bun shadcn@latest to fetch and execute the shadcn/ui CLI for component scaffolding in references/shadcn.md.
  • Fetches map styles and configuration from MapTiler's API in references/maplibre.md.
  • [COMMAND_EXECUTION]: The skill relies on shell command execution for its core functionality.
  • Instructs the agent to use bun add and bun run for dependency management and running development scripts.
  • Employs asdf set and asdf install for managing runtime versions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 03:53 PM