tooluniverse-drug-regulatory

Pass

Audited by Gen Agent Trust Hub on Mar 30, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface due to its reliance on external data sources.
  • Ingestion points: Data is ingested from external medical and regulatory APIs including FDA Orange Book, RxClass, DailyMed labels, and ClinicalTrials.gov (via tools like DailyMed_parse_adverse_reactions, FDA_OrangeBook_search_drug, and PubMed_search_articles), in addition to user-provided drug names and identifiers.
  • Boundary markers: The instructions do not specify the use of delimiters or protective instructions to isolate and disregard potential malicious prompts embedded within external drug labels or research articles.
  • Capability inventory: The skill's capabilities are restricted to specialized data retrieval tools. No high-risk operations such as arbitrary command execution, file system writes, or direct code evaluation were identified.
  • Sanitization: There is no evidence of explicit sanitization or validation logic for the content retrieved from external sources before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 30, 2026, 11:09 AM