vk-mcp
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions configure the installation and execution of the
vk-mcp-rupackage from a remote repository using theuvxcommand-line tool. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from the VK social platform, including user messages, wall posts, and community comments, which could contain adversarial instructions.
- Ingestion points: Data is retrieved from external sources via
vk_call_method(e.g., methods for reading messages, comments, or posts). - Boundary markers: The instructions do not define specific delimiters to separate external data from the agent's internal prompt instructions.
- Capability inventory: The skill has capabilities to perform network writes and account modifications, such as
wall.post,messages.send, andmarket.delete. - Sanitization: The skill instructions recommend human confirmation for irreversible actions (
groups.ban,wall.delete, etc.), which serves as a mitigation against automated exploitation.
Audit Metadata