com.a2awire/benchmark-support-agent-trials-hard
Detected by Squatch rules from the server's metadata and protocol behavior. Latest completed scan: .
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 instructs the AI model to place conversation content, prompts, tool history or secrets into tool arguments or external destinations.
First seen · Last seen
Suggested fix: Do not ask the model to include conversation, prompt or credential content in arguments.
Model-facing text references credential, key or configuration file locations unrelated to the tool's stated purpose.
First seen · Last seen
Suggested fix: Remove references to credential files, key stores and client configuration files.
Model-facing text references credential, key or configuration file locations unrelated to the tool's stated purpose.
First seen · Last seen
Suggested fix: Remove references to credential files, key stores and client configuration files.
Model-facing text instructs the AI model to place conversation content, prompts, tool history or secrets into tool arguments or external destinations.
First seen · Last seen
Suggested fix: Do not ask the model to include conversation, prompt or credential content in arguments.
Model-facing text instructs the AI model to place conversation content, prompts, tool history or secrets into tool arguments or external destinations.
First seen · Last seen
Suggested fix: Do not ask the model to include conversation, prompt or credential content in arguments.
The tool's display title describes a lower-impact action than its name (for example a read title on a delete tool).
First seen · Last seen
Suggested fix: Make the title describe the same action as the tool name.
The tool's display title describes a lower-impact action than its name (for example a read title on a delete tool).
First seen · Last seen
Suggested fix: Make the title describe the same action as the tool 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.
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.
Model-facing text contains shell command patterns such as piping downloads into a shell or recursive deletion.
First seen · Last seen
Suggested fix: Remove shell commands from descriptions.
A tool parameter asks the AI model to supply a password, token, key or similar credential, which the model can see and repeat.
First seen · Last seen
Suggested fix: Obtain credentials through server-side configuration or MCP authorization instead of tool arguments.
Model-facing text contains shell command patterns such as piping downloads into a shell or recursive deletion.
First seen · Last seen
Suggested fix: Remove shell commands from descriptions.
The tool declares itself read-only, but its name or description indicates it changes, deletes or runs something. Clients that auto-approve read-only tools would run it without confirmation.
First seen · Last seen
Suggested fix: Set readOnlyHint to false and destructiveHint to reflect the tool's behavior.
The tool declares itself read-only, but its name or description indicates it changes, deletes or runs something. Clients that auto-approve read-only tools would run it without confirmation.
First seen · Last seen
Suggested fix: Set readOnlyHint to false and destructiveHint to reflect the tool's behavior.
A tool parameter asks the AI model to supply a password, token, key or similar credential, which the model can see and repeat.
First seen · Last seen
Suggested fix: Obtain credentials through server-side configuration or MCP authorization instead of tool arguments.
A tool parameter asks the AI model to supply a password, token, key or similar credential, which the model can see and repeat.
First seen · Last seen
Suggested fix: Obtain credentials through server-side configuration or MCP authorization instead of tool arguments.
A tool parameter asks the AI model to supply a password, token, key or similar credential, which the model can see and repeat.
First seen · Last seen
Suggested fix: Obtain credentials through server-side configuration or MCP authorization instead of tool arguments.
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.
A tool parameter asks the AI model to supply a password, token, key or similar credential, which the model can see and repeat.
First seen · Last seen
Suggested fix: Obtain credentials through server-side configuration or MCP authorization instead of tool arguments.
A tool parameter asks the AI model to supply a password, token, key or similar credential, which the model can see and repeat.
First seen · Last seen
Suggested fix: Obtain credentials through server-side configuration or MCP authorization instead of tool arguments.
The tool declares itself read-only, but its name or description indicates it changes, deletes or runs something. Clients that auto-approve read-only tools would run it without confirmation.
First seen · Last seen
Suggested fix: Set readOnlyHint to false and destructiveHint to reflect the tool's behavior.
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.
Model-facing text contains shell command patterns such as piping downloads into a shell or recursive deletion.
First seen · Last seen
Suggested fix: Remove shell commands from descriptions.