pp-podcastindex

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

• Third-party content exposure detected (high risk: 0.75). The required workflow runs the podcastindex-pp-cli with --agent, which returns raw JSON from PodcastIndex (and can include transcript text via tgrep), and that upstream API content is outsider-authored free text that the agent will ingest into LLM context.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires installing and running remote binaries via go install (which fetches and compiles remote code) for the listed GitHub repositories (github.com/mvanhorn/printing-press-library/library/media-and-entertainment/podcastindex/cmd/podcastindex-pp-cli@latest and github.com/mvanhorn/printing-press-library/library/media-and-entertainment/podcastindex/cmd/podcastindex-pp-mcp@latest), so these runtime fetches execute remote code and are required dependencies.