higgsfield-generate

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). The skill workflow involves importing product information via URL (higgsfield marketing-studio products fetch --url) and fetching brand kits from website URLs (higgsfield marketing-studio brand-kits fetch --url), which ingests external web content.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill executes an untrusted remote script piped directly to a shell (curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh), introducing a weak/unknown external runtime dependency.