courier-notification-skills

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow includes fetching live documentation from https://www.courier.com/docs/llms.txt (and then fetching the referenced pages), which is public web content authored by outsiders and can be ingested as readable markdown into the agent’s LLM context.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs the agent at runtime to fetch live docs from https://www.courier.com/docs/llms.txt (and then fetch pages listed there) to resolve current API signatures, which is a runtime external dependency whose fetched content directly controls the agent's prompt/context — https://www.courier.com/docs/llms.txt is therefore flagged.