pp-podcast-goat

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

• Third-party content exposure detected (high risk: 1.00). The skill's CLI explicitly fetches and ingests transcripts from open/public third-party sources (e.g., "episode get" via the cookie -> free -> paid dispatch chain pulling from Dwarkesh Substack, YouTube/yt-dlp, Podcasting 2.0 RSS, spoken.md) and returns that content for agent consumption and decision-making (see multiple "episode get", "source compare", and batch/magic workflows in SKILL.md), so untrusted user-generated web content can influence subsequent agent actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's prerequisite steps instruct installing and running remote code—e.g., "npx -y @mvanhorn/printing-press install podcast-goat" and "go install github.com/mvanhorn/printing-press-library/library/media-and-entertainment/podcast-goat/cmd/podcast-goat-pp-cli@latest"—which fetch and execute external code at runtime and are required for the skill to operate.