skills/janjaszczak/cursor/vanilla-web/Gen Agent Trust Hub

vanilla-web

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes a shell script (scripts/serve.sh) that launches a local HTTP server using python3 -m http.server. This is a standard development practice for manual verification of static web pages.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided requirements for building web components. 1. Ingestion points: User instructions for UI components or refactoring (SKILL.md). 2. Boundary markers: The skill does not define specific delimiters for user-provided data. 3. Capability inventory: The skill generates code files and provides a script for local execution via a Python-based server (scripts/serve.sh). 4. Sanitization: No specific sanitization or validation logic is present for user-supplied requirements.
  • [SAFE]: The instructions follow standard web development best practices (ESM, SRP, semantic HTML) and do not contain any obfuscation, exfiltration, or persistence patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 01:28 PM