creative-director
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill metadata and documentation refer to an external resource hosted at
https://github.com/smixs/creative-director-skillfor the full workflow and assets. - [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to ingest and process data from untrusted sources, creating a potential vector for indirect prompt injection attacks.
- Ingestion points: Instructions in SKILL.md tell the agent to inspect HTML elements, browser tabs, design files, active design systems, attached images, and project folders.
- Boundary markers: None identified.
- Capability inventory: No scripts or direct execution capabilities are present in the skill file itself; it functions as a behavioral guide for orchestrating other agent resources.
- Sanitization: No validation or sanitization of external content is specified.
Audit Metadata