Skills
Navigate
skills/eachlabs/skills/packaging-design-generation/Gen Agent Trust Hub

packaging-design-generation

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates communication with eachsense-agent.core.eachlabs.run and storage.eachlabs.ai for design generation and asset retrieval. These resources are owned by the vendor and are necessary for the skill's intended purpose.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user descriptions and passes them to an external generation API, which constitutes a prompt injection surface. 1. Ingestion points: User-controlled strings within the messages field of the curl examples in SKILL.md. 2. Boundary markers: Absent. There are no instructions provided to delimit user input from agent-provided instructions. 3. Capability inventory: Network connectivity to the eachlabs.run API endpoint. 4. Sanitization: None. The skill does not describe any methods for validating or escaping the user-provided design descriptions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 05:14 AM