The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes data retrieved from the Monarch Initiative API, which represents a surface for indirect prompt injection where external data could potentially influence agent behavior.
Ingestion points: JSON responses from the /v3/api/association, /v3/api/search, and /v3/api/entity endpoints in SKILL.md and scripts/query_monarch.py.
Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the provided files.
Capability inventory: The skill has access to Bash(curl:*) and Bash(python:*), enabling execution of commands based on processed input.
Sanitization: There is no evidence of explicit sanitization or validation of the API data before use in the logic.
[EXTERNAL_DOWNLOADS]: The skill performs network operations to api-v3.monarchinitiative.org to fetch genomic and phenotypic association data. These requests target established research infrastructure for the skill's primary academic purpose.
[COMMAND_EXECUTION]: The skill includes a Python script (scripts/query_monarch.py) and provides code examples for the agent to execute Python and curl commands to interact with the Monarch Initiative API.

alterlab-monarch