pp-tenki

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

• Third-party content exposure detected (low risk: 0.10). The skill instructs the agent to fetch and parse public web pages from tenki.jp using a CLI tool, which represents low-risk ingestion of arbitrary web content.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the agent to install a CLI tool via npm or go install from GitHub, but the Go install URL uses a repository under the publisher user mvanhorn, which is common/reputable unofficial rather than an official project release channel.