medieval-scholasticism-expert

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill architecture and instructions are focused on providing accurate historical information. No malicious behavior, obfuscation, or sensitive data access was identified.\n- [PROMPT_INJECTION]: The skill defines a process for ingesting external data, creating a surface for indirect prompt injection.\n
  • Ingestion points: modules/research-checklist.md directs the agent to gather and distill information from Wikipedia, ArXiv, and web searches.\n
  • Boundary markers: No specific delimiters are defined to isolate external research content from internal instructions.\n
  • Capability inventory: The skill does not have access to sensitive files, system commands, or network exfiltration tools.\n
  • Sanitization: There is no explicit sanitization or validation logic for the research data content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 05:38 PM
Security Audit — agent-trust-hub — medieval-scholasticism-expert