nft-art-generation
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-supplied natural language prompts to generate NFT artwork via an external API call.
- Ingestion points: User prompts for character traits, styles, and artistic descriptions are ingested and interpolated into API request payloads as shown in
SKILL.md. - Boundary markers: The provided instructions and examples do not implement specific delimiters or safety instructions to prevent potentially malicious user input from influencing the generation logic beyond the intended scope.
- Capability inventory: The skill utilizes network capabilities to send these prompts to the
eachsense-agent.core.eachlabs.runendpoint. - Sanitization: The skill files do not specify any sanitization, filtering, or validation logic for the user-provided prompt content before it is processed by the AI model.
Audit Metadata