Список фото профиля юзера/группы/канала (метаданные, без скачивания).
AI agents call get_profile_photos 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 queries and retrieves profile photo metadata for users, groups, or channels without downloading or modifying any data. It has no side effects, making it a Read operation with low severity. An AI misusing this tool could only access metadata already associated with public or accessible profiles, posing minimal risk.
From the tool's definition Tool description states it retrieves 'Список фото профиля' (list of profile photos) with 'метаданные, без скачивания' (metadata, without downloading).
Attacks that exploit this kind of access
Список фото профиля юзера/группы/канала (метаданные, без скачивания). 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_profile_photos: 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_profile_photos 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_profile_photos 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_profile_photos. 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_profile_photos 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 →