pp-docker-hub

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

• Third-party content exposure detected (high risk: 0.80). This skill explicitly queries the Docker Hub public API (SKILL.md header: "Docker Hub public API") using commands such as "docker-hub-pp-cli docker-hub-search" and "docker-hub-pp-cli repositories " and even inspects Dockerfiles, returning user-generated repository metadata and file contents in the Agent Mode/Response envelope that the agent is expected to parse and act on, so untrusted third-party content can influence behavior.

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

• Potentially malicious external URL detected (high risk: 0.80). This skill requires fetching and installing a third‑party CLI from remote installers that will download and execute code at install time (e.g., go install github.com/mvanhorn/printing-press-library/library/developer-tools/docker-hub/cmd/docker-hub-pp-cli@latest and the npx installer @mvanhorn/printing-press), and that CLI is a required dependency for the skill to run.