seeding-playbooks

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

• Third-party content exposure detected (high risk: 0.90). The verified workflow explicitly instructs agents to run commands like "bun src/index.ts list {source-slug} --json" and "bun src/index.ts admin source fetch-log {source-slug} --json" to ingest release data and fetch logs derived from each source's public URLs (org sources), which the agent must analyze and use to generate playbook instructions—exposing it to untrusted third-party content that can influence behavior.