hf-cli

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

• Third-party content exposure detected (low risk: 0.10). The required runtime workflow is the Hugging Face Hub CLI hf as documented in SKILL.md, which only defines command interfaces and supports user-selected operations like hf download, hf discussions info, and hf spaces info but does not itself specify that the agent ingests any outsider-authored free text without an explicit selection/fetch of a specific repo/dataset/discussion by the caller.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill's install instruction downloads and pipes a remote shell script to bash (curl -LsSf https://hf.co/cli/install.sh | bash -s), which fetches and executes remote code at runtime.