Skills
Navigate
skills/eachlabs/skills/eachlabs-image-edit/Gen Agent Trust Hub

eachlabs-image-edit

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user data through text prompts and image URLs which are then passed to remote AI models.
  • Ingestion points: The prompt and image_url fields across various model configurations in references/MODELS.md.
  • Boundary markers: None present in the instructions to delineate user input from system instructions.
  • Capability inventory: The skill performs network operations via curl to api.eachlabs.ai for image processing.
  • Sanitization: No explicit sanitization or validation of the input prompt or image content is described within the skill's instructions.
  • [SAFE]: The skill uses environment variables (EACHLABS_API_KEY) for authentication, which is a recommended practice for secret management.
  • [SAFE]: Communication is directed to the vendor's official API domain (api.eachlabs.ai), matching the skill's author.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 05:55 AM