vite-flare-starter

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands such as git clone, pnpm install, and wrangler for project initialization and deployment. These are standard operations for a scaffolding tool.\n- [EXTERNAL_DOWNLOADS]: Fetches a project template from the author's GitHub repository and installs dependencies from official registries. The repository github.com/jezweb/vite-flare-starter.git is a vendor-owned resource.\n- [PROMPT_INJECTION]: Identifies a surface for indirect prompt injection where user-provided inputs are interpolated into shell commands.\n
  • Ingestion points: Project name and description are requested from the user during the initial workflow step (SKILL.md).\n
  • Boundary markers: No specific delimiters are used to wrap user-provided strings when they are used in commands.\n
  • Capability inventory: The skill utilizes shell execution (wrangler, git, pnpm) and file system modification tools.\n
  • Sanitization: No explicit sanitization is described, although the skill advises using internal edit tools as a safer alternative to shell commands for string replacement.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 04:41 AM