Skills
Navigate
skills/shipshitdev/skills/landing-page-vercel/Gen Agent Trust Hub

landing-page-vercel

Pass

Audited by Gen Agent Trust Hub on Oct 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided product information, such as names and taglines, to generate the landing page content. This data ingestion occurs during the PRD brief intake phase and via command-line arguments passed to the scaffolding script.
  • Ingestion points: SKILL.md Phase 1 (PRD Brief Intake) and scripts/scaffold.py CLI arguments.
  • Boundary markers: No specific delimiters are mandated for the intake phase.
  • Capability inventory: The skill performs local file system writes via scripts/scaffold.py and network-based deployment via the Vercel CLI.
  • Sanitization: The produced script.js uses textContent to render data from data.json, preventing script injection in the generated website.
  • [COMMAND_EXECUTION]: The skill facilitates the execution of local scripts and well-known deployment tools.
  • It uses python3 scripts/scaffold.py to generate the project structure.
  • It utilizes bunx vercel for deployment to a well-known hosting service.
  • These operations are necessary for the skill's intended functionality of creating and launching web pages.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 7, 2026, 04:47 PM