blog-post-writer

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

• Third-party content exposure detected (low risk: 0.10). The required workflow fetches https://nicknisi.com/posts at runtime to read recent posts written by Nick Nisi, which falls under fetching arbitrary web pages and content sources (low risk).

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to fetch external live content from https://nicknisi.com/posts at runtime, establishing an inbound operational dependency on an arbitrary remote web server.