a1-yandex-kit-catalog-doctor

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [SAFE]: The skill instructions and associated reference files were analyzed for malicious patterns, including prompt injection, data exfiltration, and persistence mechanisms. No such patterns were found. The skill adheres to best practices for AI agent catalog management.
  • [COMMAND_EXECUTION]: The skill utilizes several MCP (Model Context Protocol) tools to interact with a Yandex KIT server. This includes specific functions like list_products, update_variant, and a generic kit_request tool for advanced operations. All write operations are governed by the exact-write-protocol.md, which mandates an explicit authorization gate, single-stage execution for mutations, and post-write verification to prevent accidental or unauthorized changes.
  • [EXTERNAL_DOWNLOADS]: The skill includes a link to a Telegram support channel (https://t.me/a1_yandex_kit_skills). This is documented as a resource for user support and feedback and does not involve the automatic download or execution of external code or scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 01:27 PM
Security Audit — agent-trust-hub — a1-yandex-kit-catalog-doctor