artifact-open-science
Pass
Audited by Gen Agent Trust Hub on May 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues or malicious patterns were detected. The skill consists entirely of instructional markdown and YAML configuration files defining repository structures and research policies.
- [DATA_EXFILTRATION]: The skill contains proactive security policies to prevent data exposure. It explicitly instructs the agent to exclude credentials, private data, and local-only paths from public artifacts. It also defines sensitivity classes (e.g.,
personal-data,proprietary-or-licensed) to guide safe data handling. - [COMMAND_EXECUTION]: The skill does not contain any executable code or scripts. While it mentions terms like 'install command' and 'smoke test', these are listed as metadata fields for the user to populate in their own research checklists, not as commands for the agent to execute autonomously.
- [PROMPT_INJECTION]: No attempts to bypass safety filters or override system instructions were found. The instructional language is focused on standard academic workflows and reproducibility requirements.
Audit Metadata