mouse-phenome-database

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches mouse phenotype data, project metadata, and genomic coordinates from the official Jackson Laboratory Mouse Phenome Database REST API at phenome.jax.org. These requests are used to retrieve scientific datasets for analysis.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes data from an external API, which serves as a potential surface for indirect prompt injection.
  • Ingestion points: Data enters the agent's context through several requests.get() calls to the MPD API at https://phenome.jax.org/api (e.g., retrieving project info, strain means, and per-animal values in SKILL.md).
  • Boundary markers: The skill does not implement explicit boundary markers or instructions to the agent to treat the fetched scientific data as non-executable text.
  • Capability inventory: The skill possesses capabilities for network operations via the requests library and local file writing through pandas.to_csv() (e.g., creating mpd_strain_means.csv and qtl_pheno.csv).
  • Sanitization: The skill relies on standard library parsing (JSON/CSV) without applying specific content validation or sanitization to the text fields retrieved from the external database.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 12:53 AM