landing-page-scaffold

Pass

Audited by Gen Agent Trust Hub on Nov 22, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from JSON configuration files or command-line arguments to populate an HTML template.
  • Ingestion points: Data is read from the file path specified in the --config argument or directly from CLI flags like --name and --tagline in scripts/generate_landing_page.py.
  • Boundary markers: The skill does not use specific boundary markers to delimit user-provided content within the generated template.
  • Capability inventory: The script has the capability to write the generated HTML to any local file system path provided by the user and can trigger the default web browser to open local files.
  • Sanitization: The script uses html.escape() for content inserted into the HTML body and a basic bracket-stripping function for content used within CSS variables.
  • [COMMAND_EXECUTION]: The skill instructions prompt the agent to execute a local Python script (scripts/generate_landing_page.py) to perform its primary function. This script is distributed as part of the skill and does not download or execute external code.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 22, 2026, 01:11 AM