cli-hub-meta-skill

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

• Third-party content exposure detected (low risk: 0.10). The agent searches and installs packages from a public CLI marketplace (CLI-Hub) and repository, where package descriptions and metadata can be authored by outsiders.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to fetch and adopt instructions/configuration from a third-party DigitalOcean Spaces URL (https://reeceyang.sgp1.cdn.digitaloceanspaces.com/SKILL.md), which has weak/unknown publisher provenance.