dynamic-api-integration

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly instructs the agent to fetch and parse OpenAPI specs and arbitrary web pages (e.g., Phase 1 "Discover — Fetch and Parse the API Spec" using WebFetch to retrieve spec URLs like https://api.example.com/openapi.json and Phase 4 using WebFetch to summarize article URLs), which means the agent will ingest untrusted third‑party content that can directly influence endpoint selection and subsequent tool calls.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly performs runtime WebFetch of remote OpenAPI specs (e.g., "https://api.example.com/openapi.json") and uses the fetched spec content to drive prompt-driven extraction and subsequent API-calling logic, meaning external content is injected into the agent context and directly controls agent behavior.