cs-voc-triage

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from customer reviews, SNS comments, and inquiries which are susceptible to embedded malicious instructions.
  • Ingestion points: Processes data from Coupang, Naver Smartstore, YouTube, and Instagram as described in SKILL.md.
  • Boundary markers: No specific boundary markers or instructions to ignore embedded prompts are defined in the orchestration logic.
  • Capability inventory: The skill produces response templates and action plans, and integrates with downstream skills for document generation (doc-pptx) and messaging (cs-channel-message).
  • Sanitization: There is no evidence of sanitization or filtering of external text content before it is processed for sentiment and insight extraction.
  • [EXTERNAL_DOWNLOADS]: The skill references and encourages the use of various third-party APIs to gather raw VOC data.
  • Evidence: Mentions integration with Naver Commerce API, Coupang Wing API, YouTube Data API, and Instagram Graph API.
  • Context: These are standard industry APIs for the described functionality and are treated as safe service references.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 01:41 PM
Security Audit — agent-trust-hub — cs-voc-triage