cf-image
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill communicates with Cloudflare's Workers AI API via api.cloudflare.com. Cloudflare is a well-known service, and this network activity is required for the intended image generation functionality.
- [COMMAND_EXECUTION]: The skill relies on executing a bundled Python script (generate.py) to process requests and interact with the remote API.
- [INDIRECT_PROMPT_INJECTION]: The skill processes natural language input from users to generate image prompts, which represents an attack surface for indirect prompt injection.
- Ingestion points: Natural language requests from users as described in SKILL.md.
- Boundary markers: None specified in the instructions to separate user input from the agent's prompt-engineering logic.
- Capability inventory: Includes execution of local scripts, network operations via the requests library, and writing generated images to the local file system.
- Sanitization: No explicit sanitization or validation of the user-provided descriptions is performed before they are processed by the agent.
Audit Metadata