protocolsio-integration

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill explicitly shows and instructs embedding access tokens directly into Authorization headers and code (e.g., Authorization: Bearer YOUR_ACCESS_TOKEN, token = "YOUR_ACCESS_TOKEN"), which encourages the LLM to accept and place user secrets verbatim into generated requests or code, creating an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.78). The skill’s runtime workflow can ingest outsider-authored free text via protocols.io API responses that include public protocol content and community discussions (e.g., GET /protocols/{protocol_id} with content_format=html/markdown and GET /protocols/{protocol_id}/comments), where the protocol steps/descriptions and comment bodies are authored by other users.