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 core workflow (SKILL.md Phase 1 and Phase 4) explicitly instructs the agent to fetch and parse OpenAPI/spec URLs and to WebFetch arbitrary article/URL content (e.g., WebFetch({url: "...openapi.json"}) and WebFetch({url: articles[0].url, prompt: "Summarize..."})), which means it ingests untrusted public 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: 0.90). The skill explicitly fetches user-supplied OpenAPI/Swagger spec URLs at runtime (e.g., WebFetch({ url: "https:///openapi.json", prompt: "Extract all API endpoints..." })), and those fetched specs are parsed and converted into tool templates that directly control subsequent agent instructions and call behavior, so this is a runtime external dependency that can control the agent.