skills/ofoxai/skills/ofox-image-core/Gen Agent Trust Hub

ofox-image-core

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides a functional wrapper for the Ofox text-to-image API, facilitating synchronous generation requests.
  • [CREDENTIALS_SAFE]: The skill implements robust secret management by requiring the OFOX_API_KEY to be supplied via the shell environment. It explicitly forbids hardcoding, logging, or echoing the key value in any output or file.
  • [COMMAND_EXECUTION]: Legitimate use of curl and jq is observed for API interaction and JSON processing. The script references/ofox-image.sh uses jq --arg to safely handle user-supplied prompts, mitigating injection risks during request construction.
  • [EXTERNAL_DOWNLOADS]: The skill fetches model information from the vendor's official public endpoint (api.ofox.ai/v1/models) to enable client-side validation of model IDs and pricing. This activity is transparently documented and serves a functional purpose.
  • [DATA_EXFILTRATION]: Network activity is restricted to the documented vendor API. There is no evidence of the skill accessing sensitive local files or transmitting data to unauthorized third-party domains.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 07:02 AM
Security Audit — agent-trust-hub — ofox-image-core