higgsfield-video-explainer

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

• Third-party content exposure detected (low risk: 0.10). The workflow allows reading local source documents and performing web research via available tools, but it does not automatically consume untrusted outsider-authored feeds or queues.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to download and execute an installation script from https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh, representing a weak/unknown/suspicious operational dependency via a remote shell script execution.