rw-research-question
Pass
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a structured academic methodology with clear operational boundaries. It explicitly instructs the agent to avoid accessing private user workspaces, personal vaults, or local environment files unless materials are explicitly provided by the user for the current task context.
- [EXTERNAL_DOWNLOADS]: The skill contains references to official documentation from established research organizations, including Cochrane Training, JBI Global, and the EQUATOR Network. These references are used for information verification and do not involve the download or execution of untrusted scripts or binary content.
- [NO_CODE]: A Python validation script (
scripts/self_check.py) is included to ensure the integrity of the skill's file structure and adherence to standalone rules. This script is a static utility and is not used to process untrusted user input or perform network exfiltration.
Audit Metadata