gemini-image

Warn

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill transmits user data and authentication tokens to an external API at api.apicore.ai. This service is not on the whitelisted domains or recognized as a well-known service.
  • [COMMAND_EXECUTION]: Employs the curl utility to execute HTTP POST requests for image generation.
  • [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection.
  • Ingestion points: It takes user-provided descriptions and image URLs directly from the agent context in SKILL.md.
  • Boundary markers: It lacks explicit boundary markers or instructions for the agent to ignore control commands embedded in the user-provided prompt or image URLs.
  • Capability inventory: The skill has the capability to perform network requests via curl across the provided scripts.
  • Sanitization: There is no evidence of sanitization, validation, or escaping of the external content before it is interpolated into the API call.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 20, 2026, 12:29 PM
Security Audit — agent-trust-hub — gemini-image