agri-paper
Pass
Audited by Gen Agent Trust Hub on Jul 26, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves processing untrusted external content such as manuscripts and research data.
- Ingestion points: Ingests user-provided agricultural manuscripts, field trial data, and animal/soil work descriptions.
- Capability inventory: Includes execution of citation verification scripts and delegation to multiple specialized sub-agents for statistics, data curation, and literature review.
- Boundary markers: No explicit delimiters or boundary warnings are defined in this wrapper; safety relies on the inherited 'food-paper' infrastructure.
- Sanitization: The skill does not describe explicit sanitization or escaping methods for the data it processes.
- [COMMAND_EXECUTION]: The skill references a local Python script
scripts/verify_citations.py. This is an internal component used to validate academic citations and does not involve remote code downloads.
Audit Metadata