cs-channel-message

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data such as advertising performance reports, seasonal keyword calendars, and persona definitions to generate tailored marketing content.\n
  • Ingestion points: External data is imported via attached files, screenshots, or MCP connectors as specified in the '개요' and '워크플로우' sections of SKILL.md.\n
  • Boundary markers: The skill does not implement explicit boundary markers (e.g., XML tags or specific delimiters) or 'ignore instructions' warnings for the ingested data.\n
  • Capability inventory: The skill possesses text generation capabilities and triggers automated chaining to other agents such as 'moai-coworker:ai-slop-reviewer' and 'moai-writer:korean-humanize'.\n
  • Sanitization: There is no evidence of data sanitization, schema validation, or filtering for the external reports before they are processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 01:42 PM
Security Audit — agent-trust-hub — cs-channel-message