socratic-learning

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill's design involves ingesting data from external sources (webpages, repositories, transcripts) which presents an indirect prompt injection surface. * Ingestion points: Defined in references/knowledge-base.md, including web searches and repository extraction. * Boundary markers: The skill does not define specific delimiters for separating user-provided source material from agent instructions. * Capability inventory: Primarily restricted to conversational tutoring and framing, though it suggests the use of external content extraction tools. * Sanitization: No explicit sanitization of external source content is specified.
  • [EXTERNAL_DOWNLOADS]: The credits.md file references external GitHub repositories for attribution and methodology grounding. These links point to well-known services and are used for documentation purposes.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 11:26 AM
Security Audit — agent-trust-hub — socratic-learning