Severity: HighStatus: OpenSQ-TOOL-EXFIL-SHAPED-PARAM
Free-text parameter commonly used to collect conversation data
A free-text parameter has a name commonly abused to collect conversation, prompt or environment data.
First seen · Last seen
Findings
Detected by Squatch rules from the server's metadata and protocol behavior. Latest completed scan: .
Severity: High3 findings
Suggested fix: Constrain the parameter (enum, maxLength) or rename it to reflect its purpose; never ask the model to fill it with conversation content.
Severity: HighStatus: OpenSQ-TOOL-EXFIL-SHAPED-PARAM
Free-text parameter commonly used to collect conversation data
A free-text parameter has a name commonly abused to collect conversation, prompt or environment data.
First seen · Last seen
Suggested fix: Constrain the parameter (enum, maxLength) or rename it to reflect its purpose; never ask the model to fill it with conversation content.
Severity: HighStatus: OpenSQ-TOOL-EXFIL-SHAPED-PARAM
Free-text parameter commonly used to collect conversation data
A free-text parameter has a name commonly abused to collect conversation, prompt or environment data.
First seen · Last seen
Suggested fix: Constrain the parameter (enum, maxLength) or rename it to reflect its purpose; never ask the model to fill it with conversation content.
Severity: Medium10 findings
Severity: MediumStatus: OpenSQ-SERVER-AUTH-NONE-WRITE
State-changing tools available without authentication
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.
Severity: MediumStatus: OpenSQ-TOOL-ANNOTATION-DESTRUCTIVE-UNDERCLAIM
Declared non-destructive but appears to delete data
The tool declares destructiveHint false, but its name or description indicates it deletes data.
First seen · Last seen
Suggested fix: Set destructiveHint to true.
Severity: MediumStatus: OpenSQ-TOOL-ANNOTATION-DESTRUCTIVE-UNDERCLAIM
Declared non-destructive but appears to delete data
The tool declares destructiveHint false, but its name or description indicates it deletes data.
First seen · Last seen
Suggested fix: Set destructiveHint to true.
Severity: MediumStatus: OpenSQ-TOOL-INJECTION-INSTRUCTIONS
Instructions addressed to the AI model
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.
Severity: MediumStatus: OpenSQ-TOOL-INJECTION-INSTRUCTIONS
Instructions addressed to the AI model
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.
Severity: MediumStatus: OpenSQ-TOOL-INJECTION-INSTRUCTIONS
Instructions addressed to the AI model
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.
Severity: MediumStatus: OpenSQ-TOOL-INJECTION-INSTRUCTIONS
Instructions addressed to the AI model
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.
Severity: MediumStatus: OpenSQ-TOOL-INJECTION-INSTRUCTIONS
Instructions addressed to the AI model
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.
Severity: MediumStatus: OpenSQ-TOOL-INJECTION-INSTRUCTIONS
Instructions addressed to the AI model
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.
Severity: MediumStatus: OpenSQ-TOOL-INJECTION-INSTRUCTIONS
Instructions addressed to the AI model
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.
Severity: Low5 findings
Severity: LowStatus: OpenSQ-CONFORMANCE-MODERN-FAILURE
Protocol conformance checks failed
The server failed one or more MCP protocol conformance checks.
First seen · Last seen
Suggested fix: Review the failed checks against the MCP specification.
Severity: LowStatus: OpenSQ-TOOL-ANNOTATION-UNDERCLAIM
Annotations understate what the tool does
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.
Severity: LowStatus: OpenSQ-TOOL-META-INSUFFICIENT
Description too thin to determine 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.
Severity: LowStatus: OpenSQ-TOOL-META-INSUFFICIENT
Description too thin to determine 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.
Severity: LowStatus: OpenSQ-TOOL-META-INSUFFICIENT
Description too thin to determine 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.
What this scan does not cover
- Squatch never calls a server's tools, so it cannot see what they actually do at run time.
- It scans without credentials: tools behind authentication may not be visible.
- It does not review source code, dependencies or the publisher's infrastructure.
- A server can change behavior between scans; monitoring compares each scan with the last.
- Classifications come from tool names, descriptions and schemas, which the publisher controls.