spec2cli-basics

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

• Third-party content exposure detected (high risk: 0.75). The required workflow includes loading a spec from a user-supplied remote URL (spec2cli --spec https://...), and that fetched page/content (the OpenAPI/Swagger text) is then ingested by the agent/LLM to generate help/commands, which is outsider-authored free text from public web content.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly fetches an OpenAPI spec at runtime (e.g., https://api.example.com/openapi.json) and its --agent-help mode returns AI-optimized YAML that would be consumed by an agent, meaning remote spec content can directly control prompts/behavior.