Text asks the AI model to hide actions from the user
Model-facing text instructs the AI model to hide actions or information from the user.
First seen · Last seen
Detected by Squatch rules from the server's metadata and protocol behavior. Latest completed scan: .
Model-facing text instructs the AI model to hide actions or information from the user.
First seen · Last seen
Suggested fix: Remove any wording that asks the model to act silently or withhold information from the user.
The name closely resembles a well-known publisher; it is not published under that publisher's verified namespace.
First seen · Last seen
Suggested fix: Publishers can respond to this finding; use a distinct name.
The remote server lists state-changing tools without requiring authentication.
First seen · Last seen
Suggested fix: Require MCP authorization for servers that expose state-changing tools.
The tool's name and description do not state what it does.
First seen · Last seen
Suggested fix: Describe the action the tool performs, its target and its side effects.
The tool's name and description do not state what it does.
First seen · Last seen
Suggested fix: Describe the action the tool performs, its target and its side effects.
The tool's name and description do not state what it does.
First seen · Last seen
Suggested fix: Describe the action the tool performs, its target and its side effects.
The tool's name and description do not state what it does.
First seen · Last seen
Suggested fix: Describe the action the tool performs, its target and its side effects.