hf-cli

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly exposes the agent to public, user-generated content (e.g., "hf skills add" to download/ install marketplace skills, "hf extensions install" from public GitHub, "hf models/datasets/papers card/read" and "hf discussions" or "hf spaces" commands) which the agent would fetch and read as part of its workflow and could materially change behavior or tool use.