The Agent Skills Directory

[SAFE]: No malicious patterns or security vulnerabilities were identified in the skill instructions or scripts.- [CREDENTIALS_UNSAFE]: The skill mentions a public demo key (api2demo) for testing purposes and follows best practices by recommending environment variables (EUROPEANA_API_KEY) for production credentials.- [EXTERNAL_DOWNLOADS]: The skill communicates with the official Europeana API (api.europeana.eu), which is a well-known and trusted cultural heritage platform.- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from an external API (Europeana). While this represents a potential injection surface, the risk is mitigated as the skill does not use the ingested data in sensitive operations like code execution or file writing.
Ingestion points: EuropeanaAPI._get_json (scripts/europeana_api.py)
Boundary markers: None present for external data
Capability inventory: Data retrieval and summarization (text output); no file-write or shell execution tools are utilized with external content
Sanitization: Standard JSON parsing via the json library

europeana-collections