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.
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.
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.
Model-facing text contains instructions addressed to the AI model rather than a description of the tool (for example to override prior instructions, to act before using tools, or to react to trigger phrases).
First seen · Last seen
Suggested fix: Describe what the tool does and its parameters. Do not include instructions to the model about other tools, the user or the conversation.
The server's instructions field contains directives addressed to the AI model beyond describing how to use the server.
First seen · Last seen
Suggested fix: Limit server instructions to usage guidance for this server's own tools.
Model-facing text gives the AI model instructions about tools that this server does not provide (tool shadowing).
First seen · Last seen
Suggested fix: Describe only this server's own tools.