Creative Strategist
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill acts as a reference framework for other skills, defining how to interpret marketing data and generate creative assets. It does not contain executable code, suspicious network operations, or sensitive file access.
- [INDIRECT_PROMPT_INJECTION]: The skill contains logic for analyzing external data, specifically ad transcripts and competitor brand context. While these are ingestion points for untrusted data, the skill has no dangerous capabilities (such as shell execution or file system modification) that could be exploited. It primarily produces structured text output (briefs and concepts) based on its analysis.
- Ingestion points: Processes data from the Motion API, including ad transcripts and competitive brand context.
- Boundary markers: None explicitly specified for data processing.
- Capability inventory: Text analysis and generation of creative briefs, hooks, and concepts. No subprocess or file-write capabilities are present.
- Sanitization: Standard LLM processing is used; no explicit sanitization logic for ingested text is described.
Audit Metadata