creative-director

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches design specifications (DESIGN.md) from the domain getdesign.md. This functionality is used to provide the agent with creative vocabulary and inspiration based on real-world design systems.
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection through its ingestion of external data.
  • Ingestion points: Untrusted content is fetched from https://getdesign.md/{company}/design-md as described in SKILL.md and references/design-inspirations.md.
  • Boundary markers: The instructions do not specify the use of clear delimiters or warnings to ignore embedded instructions within the fetched markdown content.
  • Capability inventory: The skill's capabilities are limited to generating creative text, descriptions, and rationales. It does not have access to tools for file system modification, network exfiltration of local data, or arbitrary command execution.
  • Sanitization: There is no evidence of filtering or sanitization performed on the fetched external content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 06:26 AM