tooluniverse-adverse-event-detection
Pass
Audited by Gen Agent Trust Hub on May 29, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill processes data from various external medical databases such as FAERS, FDA labels, and PubMed, which represents a potential surface for indirect prompt injection. Ingestion points include drug reaction reports and clinical literature abstracts. Boundary markers and specific sanitization steps for this external content are not explicitly detailed in the prompt instructions.
- [COMMAND_EXECUTION]: The skill workflow involves generating and executing Python code via a shell interface to perform statistical calculations like Disproportionality Analysis. This dynamic execution is intended for processing safety data using established scientific libraries like pandas and scipy.
Audit Metadata