The Agent Skills Directory

[SAFE]: The skill serves as a reference for integrating with a legitimate scientific platform (protocols.io). All API endpoints use official domains (protocols.io, apidoc.protocols.io).
[SAFE]: Authentication procedures follow industry standards (OAuth 2.0 and Bearer tokens), with appropriate guidance for secure token management and instructions to avoid exposing credentials in version control.
[SAFE]: Code examples and workflows describe standard functionality for protocol and file management without any suspicious command execution, privilege escalation, or persistence mechanisms.
[SAFE]: The skill involves consuming external data (e.g., user comments), which is a common surface for indirect prompt injection. This is evaluated as safe given the context of the integration and the use of official documentation sources.
Ingestion points: references/protocols_api.md (GET /protocols), references/discussions.md (GET /comments), and references/additional_features.md (GET /notifications).
Boundary markers: Delimiters are not explicitly specified in the integration guidance provided to the agent.
Capability inventory: The skill enables interaction with the protocols.io API and management of files within the laboratory workspace.
Sanitization: No explicit sanitization or filtering of API response content is described in the reference material.

protocolsio-integration