launch-marketing

Pass

Audited by Gen Agent Trust Hub on Feb 19, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • PROMPT_INJECTION (LOW): The skill processes untrusted user data into generated marketing plans through an indirect prompt injection surface.\n
  • Ingestion points: Data enters through the question bank in references/INTAKE.md and user-provided launch context.\n
  • Boundary markers: Absent; the template structure in references/TEMPLATES.md directly interpolates user input into generated Markdown without delimiters.\n
  • Capability inventory: Limited to text generation; SKILL.md mentions file creation as a potential output format, but no scripts are provided to execute this directly.\n
  • Sanitization: No input validation or escaping is present in the workflow.\n- NO_CODE (SAFE): The skill consists entirely of descriptive Markdown files and contains no executable code or script files.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 19, 2026, 03:52 PM