podcast-creator

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflow (SKILL.md Step 2 "Upload Content" and references/content-guide.md) explicitly accepts and ingests web URLs/Google Doc links and uses that third‑party content to generate audio and downstream publishing, exposing the agent to untrusted user-provided web content that could carry indirect prompt-injection instructions.