higgsfield-generate

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.80). shop.example.com/sneakers is a benign-looking (placeholder) product page, but the raw GitHub link points to a downloadable install.sh (a direct shell script) which is high-risk to curl|sh or execute unless the repository and author are verified — so the set includes a suspicious download source.

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests arbitrary public product pages via the Marketing Studio URL flow (e.g., "higgsfield marketing-studio products fetch --url ..." in SKILL.md and references/marketing-products.md), so untrusted third-party content (page title/description/images) is read and used to drive generation and tool actions.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill's bootstrap step runs remote code via curl https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh to install the required higgsfield CLI, which fetches and executes a script at runtime, directly executing remote code.