researcher
Pass
Audited by Gen Agent Trust Hub on Feb 15, 2026
Risk Level: LOW
Full Analysis
- NO_CODE (SAFE): The skill contains only Markdown documentation files (
.md). There are no scripts, binaries, or configuration files that trigger execution. - PROMPT_INJECTION (SAFE): No instructions targeting agent behavior override or safety filter bypass were detected. Instructional comments within the paper notes (e.g.,
<!-- EXAMPLE COMMENT -->) are descriptive of formatting rather than behavioral commands. - DATA_EXFILTRATION (SAFE): No sensitive file paths, hardcoded credentials, or suspicious network requests were found. File paths mentioned (e.g.,
docs/literature/) are local documentation references. - EXTERNAL_DOWNLOADS (SAFE): All URLs provided are static links to reputable academic and government sources (PubMed, DOI, NCBI). No remote code download-and-execute patterns are present.
- INDIRECT_PROMPT_INJECTION (SAFE): While the files provide guidance on how to use other scientific skills (e.g.,
pubmed-database), they do not contain embedded malicious instructions designed to trigger side effects when processed by an agent.
Audit Metadata