Информация о настроенном 2FA-пароле (включён ли, hint, recovery email).
AI agents call get_password_info to retrieve information from Claudegram without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only queries and retrieves metadata about 2FA settings—no side effects, no data modification, no state changes. It is informational only. Severity is low because while 2FA configuration details are somewhat sensitive, reading them locally from the user's own account carries minimal risk compared to other credential or account actions.
From the tool's definition Tool name is 'get_password_info' and description states it retrieves 'information about configured 2FA password (whether enabled, hint, recovery email)'. The verb 'get' and the retrieving of status/metadata without modification indicates a read operation.
Attacks that exploit this kind of access
Информация о настроенном 2FA-пароле (включён ли, hint, recovery email). It is categorised as a Read tool in the Claudegram MCP Server, which means it retrieves data without modifying state.
Register the Claudegram MCP server in PolicyLayer and add a rule for get_password_info: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Claudegram. Nothing to install.
get_password_info is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_password_info rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for get_password_info. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
get_password_info is provided by the Claudegram MCP server (sanjar-x/claudegram). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →