kb-article

Pass

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [SAFE]: No malicious code, scripts, or binary files are included in the skill. All content consists of informational markdown templates and documentation guidelines.
  • [NO_CODE]: The skill does not ship with any executable code or scripts, relying entirely on natural language instructions for the agent.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it is designed to ingest and process untrusted data from customer support tickets and existing documents.
  • Ingestion points: Customer inquiry data ("티켓 원문") and current documentation ("현재 문서") mentioned in the problem-solving section of SKILL.md.
  • Boundary markers: Absent; the instructions do not specify delimiters (e.g., XML tags or delimiters) to separate ingested data from the agent's internal logic.
  • Capability inventory: Limited to text generation for articles; the skill lacks access to the file system, network operations, or shell execution.
  • Sanitization: Absent; there is no evidence of input filtering or validation for the external content provided at runtime.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 13, 2026, 11:43 PM