pp-goodreads

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

• Third-party content exposure detected (high risk: 0.75). The required workflow is to invoke the local goodreads-pp-cli binary (via --agent), which fetches Goodreads pages/data at runtime; that fetched page content is outsider-authored free text (public web content) and is ingested into the agent’s LLM context through the CLI’s JSON results/provenance envelope.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill's prerequisites explicitly instruct installing and running remote code at runtime via "npx -y @mvanhorn/printing-press-library install goodreads --cli-only" and "go install github.com/mvanhorn/printing-press-library/library/media-and-entertainment/goodreads/cmd/goodreads-pp-cli@latest", which fetch and execute external code that the skill requires.