evidence-level-ranker
Pass
Audited by Gen Agent Trust Hub on May 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of markdown guidelines and reference files for medical literature appraisal. No executable scripts, binaries, or shell commands were found.
- [DATA_EXFILTRATION]: The skill references a public GitHub repository (
https://github.com/aipoch/medical-research-skills) for source documentation. This is a legitimate vendor resource associated with the author and does not constitute a data exfiltration risk. - [INDIRECT_PROMPT_INJECTION]: The skill processes external data in the form of research papers provided by users. Although it lacks explicit boundary markers or sanitization instructions, the skill does not have access to sensitive tools or network capabilities that could be exploited via indirect injection, posing no functional security risk.
- [PROMPT_INJECTION]: No instructions were found that attempt to override system safety guidelines, extract system prompts, or bypass agent constraints.
Audit Metadata