systematic-review-assistant
Pass
Audited by Gen Agent Trust Hub on Apr 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of instructional text and markdown templates. It does not contain any executable scripts, binary files, or hidden commands. No patterns of data exfiltration, obfuscation, or malicious intent were found.\n- [EXTERNAL_DOWNLOADS]: The skill documentation contains an installation command
npx skills add Open-Medica/open-medical-skills. This command references the official repository of the author (Open-Medica) and is a standard mechanism for installing medical AI skills within this ecosystem.\n- [PROMPT_INJECTION]: The skill is designed to process and synthesize data from external research papers and abstracts. This creates a surface for potential indirect prompt injection where malicious instructions could be embedded in the processed medical literature. However, because the skill lacks high-risk capabilities like arbitrary command execution or network exfiltration, the risk is negligible.
Audit Metadata