creativeclaw-seedream-5-pro
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data that could contain malicious instructions.
- Ingestion points: The agent ingests data through
image_urlandextras.image_urlsparameters specified inSKILL.md. - Boundary markers: Absent. The instructions do not provide delimiters or negative constraints to prevent the agent from following instructions embedded in the metadata or content of the source images.
- Capability inventory: The skill leverages the
creative-clawMCP tool (agents/openai.yaml) and performs image generation via theimage/seedream-5-promodel. - Sanitization: Absent. No explicit validation or filtering of input image content or metadata is described.
- [EXTERNAL_DOWNLOADS]: The skill defines a dependency on an MCP tool hosted at
https://app.creativeclaw.co/mcp/chatgpt. This service is a vendor-owned resource associated with the Creative Claw platform.
Audit Metadata