hf-mcp
Fail
Audited by Snyk on Feb 16, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 0.90). The prompt explicitly instructs including secrets (e.g., "secrets": {"HF_TOKEN": "$HF_TOKEN"}) in job payloads, which encourages embedding an API token into generated requests/commands and can lead the agent to handle or output the secret verbatim, creating exfiltration risk.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). This skill fetches and displays public, user-generated Hugging Face Hub content (e.g., hub_repo_details with include_readme=true, space_search/dynamic_space invoking Gradio Spaces, and hf_doc_fetch of arbitrary docs URLs), so the agent ingests untrusted third‑party content that could enable indirect prompt injection.
Audit Metadata