poster-design-generation
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references and interacts with official vendor domains
eachsense-agent.core.eachlabs.runandstorage.eachlabs.aifor generating and retrieving media assets. These network operations are core to the skill's functionality. - [INDIRECT_PROMPT_INJECTION]: The skill has an indirect prompt injection surface through user-defined messages and external image URLs. Ingestion points: User-provided text prompts and external image URLs in the
curlexamples found inSKILL.md. Boundary markers: The instructions do not specify explicit delimiters for untrusted input. Capability inventory: The skill facilitates network requests to the EachLabs API for image generation. Sanitization: Safety is managed by the API's content policies as described in the error handling documentation.
Audit Metadata