protocolsio-integration

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

• Third-party content exposure detected (high risk: 0.85). This skill’s required runtime workflow calls the public protocols.io REST API to retrieve protocol JSON (including step descriptions and other free-text fields), which is outsider-authored content that can be injected into the agent’s LLM context when the agent ingests/prints those fields.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill issues runtime HTTP requests to the protocols.io API (e.g., https://www.protocols.io/api/v4 and the endpoint https://www.protocols.io/api/v4/protocols which is called at runtime) to fetch protocol step-by-step instructions that would directly control prompts or downstream automation.