learning-methodology
Pass
Audited by Gen Agent Trust Hub on Apr 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional and logic-based. It establishes strong internal guardrails, such as prohibiting web searches, preventing hallucination, and enforcing interaction limits to avoid infinite loops.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data (PDF, TXT, and MD files) provided by the user for synthesis and tutoring.
- Ingestion points: Data ingestion occurs in
SKILL.mdunder 'Step 1: 소스 종합' and '소스 자료 처리 지침'. - Boundary markers: Absent. The instructions do not specify the use of delimiters or warnings to ignore instructions embedded within the source documents.
- Capability inventory: The skill lacks dangerous capabilities. It does not perform network requests, file system writes, or subprocess executions.
- Sanitization: Absent. No explicit sanitization or filtering logic is defined for the content extracted from processed files.
Audit Metadata