The Agent Skills Directory

[SAFE]: No malicious patterns or security risks were detected in the skill's instructions, metadata, or scripts.
[EXTERNAL_DOWNLOADS]: The skill performs network requests to the official Open Targets Platform GraphQL API (api.platform.opentargets.org). This is a well-known and reputable scientific service provided by a consortium including the European Bioinformatics Institute (EMBL-EBI) and the Wellcome Sanger Institute.
[DATA_EXFILTRATION]: No patterns of unauthorized data access or exfiltration were found. The skill does not access sensitive local files (e.g., SSH keys, AWS credentials) or environment variables.
[COMMAND_EXECUTION]: The Python scripts provided do not use any dangerous functions for executing system commands (such as subprocess, eval, or exec). Operations are limited to standard HTTP requests and JSON processing.
[PROMPT_INJECTION]: The skill's instructions focus on legitimate data retrieval and do not contain any attempts to override agent safety guidelines or system prompts.

opentargets-database