personal-event

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill mentions the use of mcp__sequential-thinking__sequentialthinking for complex reasoning tasks. This is a standard tool invocation for problem-solving within the platform's supported capabilities.
  • [EXTERNAL_DOWNLOADS]: The skill provides links to official South Korean government websites (price.go.kr and www.price.go.kr) for consumers to compare wedding service prices. These are well-known, legitimate services used for informational purposes.
  • [DATA_EXFILTRATION]: No instances of data exfiltration were found. The skill operates locally by creating and organizing planning documents within a specified _workspace/ directory.
  • [PROMPT_INJECTION]: The instructions follow a structured, professional planning workflow. There are no attempts to bypass safety filters, extract system prompts, or override agent constraints.
  • [REMOTE_CODE_EXECUTION]: The skill does not download or execute remote scripts. It orchestrates internal tasks between designated roles (Planner, Consultant, Manager) to generate text-based artifacts.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 01:41 PM
Security Audit — agent-trust-hub — personal-event