avito-listings

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill suggests the installation of an external Python package marketplaces-mcp-ru using the uvx tool to enable functionality. This package appears to be a resource provided by the vendor.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources (Avito listings, stats, and orders) which provides a surface for indirect prompt injection. * Ingestion points: External data is ingested through methods such as avito_get_item_info, avito_get_items_info, and avito_get_orders as listed in SKILL.md. * Boundary markers: The instructions do not define explicit boundary markers or directions for the agent to ignore instructions embedded in the external data. * Capability inventory: The skill provides capabilities for write operations, specifically avito_update_price and avito_put_item_vas, although it notes a user confirmation requirement. * Sanitization: No specific sanitization or filtering logic for external listing content is defined within the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 10:15 PM