openapi-directory-first

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflow (SKILL.md) explicitly requires fetching OpenAPI specs from the public APIs‑guru/openapi-directory (e.g., https://raw.githubusercontent.com/APIs-guru/openapi-directory/main/APIs/{provider.com}/{version}/openapi.yaml and https://api.apis.guru/v2/list.json), which are untrusted third‑party files the agent must read and use to determine endpoints, auth, and requests—so crafted specs could materially influence actions.

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 to fetch OpenAPI specs at runtime (e.g., https://raw.githubusercontent.com/APIs-guru/openapi-directory/main/APIs/{provider.com}/{version}/openapi.yaml and https://api.apis.guru/v2/list.json via the GitHub/API endpoints) and to use those fetched specs as the authoritative source to drive its API-calling behavior, meaning remote content directly controls prompts/instructions.