creative-director

Pass

Audited by Gen Agent Trust Hub on Sep 24, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze creative content, which can serve as a vector for indirect prompt injection.
  • Ingestion points: User-provided creative briefs and concepts processed via triggers like 'campaign concept' or 'creative critique' (SKILL.md).
  • Boundary markers: No specific delimiters or safety instructions are defined to separate user input from the agent's instructions.
  • Capability inventory: No tools, scripts, or system command access are requested in this specific metadata file.
  • Sanitization: There is no defined input validation or filtering logic.
  • [EXTERNAL_DOWNLOADS]: The skill references an external source for its primary assets and workflow logic.
  • Source: https://github.com/smixs/creative-director-skill provided in the frontmatter and documentation sections.
  • Note: The file instructs users to manually inspect and install the upstream bundle; it does not contain automated download or execution code.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 24, 2026, 06:00 AM