indication-dossier
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides structured instructions for a research workflow and does not include any executable code, shell commands, or network operations targeting untrusted domains. References to biomedical databases are limited to well-known repositories.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external research literature and biomedical databases. 1. Ingestion points: External biomedical databases (Open Targets, ChEMBL, etc.) and literature. 2. Boundary markers: No delimiters or ignore-instructions warnings are defined. 3. Capability inventory: File-write capability to the outputs/ directory. 4. Sanitization: No data sanitization or validation methods are specified.
Audit Metadata