novelty-assessment

Pass

Audited by Gen Agent Trust Hub on Feb 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE] (SAFE): The skill performs legitimate academic tasks and follows expected patterns for research automation. It utilizes local Python scripts and academic APIs.
  • [Indirect Prompt Injection] (LOW): The skill ingests untrusted user input in the form of research ideas which are then interpolated into LLM prompts. Ingestion points: The research idea is passed via the $0 argument and the {idea_description} prompt variable. Boundary markers: None are present in the provided templates to isolate the user input from the surrounding instructions. Capability inventory: The skill executes local Python scripts (novelty_check.py, search_semantic_scholar.py) and performs network-based literature searches. Sanitization: No explicit sanitization or escaping of the research idea input is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 20, 2026, 05:23 AM