skills/aipoch/medical-research-skills/conventional-non-oncology-hub-gene-research-planner/Gen Agent Trust Hub
conventional-non-oncology-hub-gene-research-planner
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill instructions contain strong constraints to prevent the agent from providing clinical advice or fabricating literature, which acts as a safety measure. It also includes explicit scope-checking logic to redirect off-topic requests.
- [DATA_EXPOSURE]: The skill references established scientific and medical resources such as PubMed, GEO, and STRING for research data. There are no patterns suggesting exfiltration of sensitive local data or hardcoded credentials.
- [INDIRECT_PROMPT_INJECTION]: While the skill ingests user-provided disease and process information to generate plans, it lacks exploitable capabilities like network exfiltration, arbitrary command execution, or file system writes. The research design generation is restricted to text output based on predefined templates.
- [EXTERNAL_DOWNLOADS]: External references target well-known scientific platforms (NCBI, GeneCards, MSigDB) and the author's official GitHub repository, which is standard for documentation and research support.
Audit Metadata