hugging-face

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

• Third-party content exposure detected (low risk: 0.10). The agent retrieves Hugging Face public content such as daily papers and dataset rows via the Hugging Face API, which constitutes public registry/community data ingestion.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill executes npx @useclawlink/cli, which fetches and runs external CLI packages from npm at runtime without version pins or cryptographic verification, introducing an unverifiable third-party operational dependency assigned a high risk tier.