landing-page-generator

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes a local Python script (scripts/landing_page_scaffolder.py) for component generation and references an external script (marketing-skill/content-production/scripts/brand_voice_analyzer.py) to be used for brand voice analysis. These executions are functional requirements for the skill's primary task of code generation and brand analysis.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) as it processes untrusted user input to generate marketing copy and components.\n
  • Ingestion points: Product name, tagline, audience, and pain point fields in the Triggering section of SKILL.md.\n
  • Boundary markers: Absent; the workflow does not use delimiters for untrusted input.\n
  • Capability inventory: File system write operations via scripts/landing_page_scaffolder.py and dynamic React/TSX code generation by the agent.\n
  • Sanitization: No sanitization is specified in the prompt instructions, although the included Python script implements HTML escaping for HTML-formatted output.\n- [SAFE]: No high-risk indicators such as hardcoded credentials, obfuscation, or unauthorized network operations were detected. The Python script relies solely on standard libraries and performs string-based code templating.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 05:28 PM
Security Audit — agent-trust-hub — landing-page-generator