Назначить участника администратором с заданными правами.
AI agents use promote_admin to create or update resources in Claudegram — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Claudegram environment.
This tool grants admin privileges to a chat participant, which is a reversible write operation (admins can be demoted). However, it carries high severity because misuse could allow an AI agent to hand over control of a Telegram group/channel to arbitrary users, potentially enabling further abuse at scale.
From the tool's definition promote_admin — 'Назначить участника администратором с заданными правами' (Appoint a member as administrator with specified rights)
Attacks that exploit this kind of access
Назначить участника администратором с заданными правами. It is categorised as a Write tool in the Claudegram MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Claudegram MCP server in PolicyLayer and add a rule for promote_admin: 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.
promote_admin is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the promote_admin 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 promote_admin. 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.
promote_admin 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 →