tattoo-design-generation
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data which could potentially contain malicious instructions. 1. Ingestion points: Data is ingested from external image URLs in SKILL.md and web search results documented in references/SSE-EVENTS.md. 2. Boundary markers: The skill instructions do not include explicit delimiters or safety instructions to distinguish between core prompts and untrusted external content. 3. Capability inventory: The skill is designed to call external generative AI APIs. 4. Sanitization: There is no evidence of validation, filtering, or sanitization of the content retrieved from remote URLs or search citations.
- [DATA_EXFILTRATION]: User prompt data and authentication credentials are sent to external infrastructure. 1. Network operations: The skill documentation describes sending data to eachsense-agent.core.eachlabs.run and storage.eachlabs.ai. 2. Sensitive data: The skill utilizes the EACHLABS_API_KEY environment variable within the X-API-Key header for authentication. 3. Author context: The targeted domains belong to the skill author (eachlabs), and these operations are essential for the primary functionality of the skill.
Audit Metadata