monarch-database
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches genomic and phenotypic data from the Monarch Initiative's official API (
api-v3.monarchinitiative.org). This is a recognized scientific resource for rare disease research and cross-species modeling. - [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes data from external API responses, which represents a potential attack surface for indirect prompt injection. However, the risk is minimal as the skill performs data transformation and visualization without dangerous side effects.
- Ingestion points: External data is retrieved via the
monarch_getandrequests.getfunctions throughoutSKILL.mdandreferences/phenotype_ontology.md. - Boundary markers: The skill does not implement specific boundary markers or warnings to the agent to ignore instructions embedded in the biological data.
- Capability inventory: Capabilities are limited to network GET requests and local data processing using
pandas; there are no file-write operations, subprocess calls, or dynamic code execution. - Sanitization: The skill processes data as structured JSON without explicit sanitization or filtering of text fields.
Audit Metadata