The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes data from the Konecty API, creating an indirect prompt injection surface where malicious records could influence agent behavior. Ingestion points: API responses are fetched in scripts/find.py via _do_request. Boundary markers: None are present to distinguish API data from system instructions. Capability inventory: The skill performs network requests using urllib and reads configuration from ~/.konecty/.env in scripts/find.py. Sanitization: The script does not sanitize or filter the content of the API response before returning it to the agent context.
[SAFE]: No malicious behavior or traditional attack vectors were detected. The script uses standard libraries and performs actions consistent with its stated purpose of searching a database via a REST API.

konecty-find