Skip to content
Squatch MCP

Findings

Detected by Squatch rules from the server's metadata and protocol behavior. Latest completed scan: .

Severity: Critical2 findings

Severity: CriticalStatus: 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: CriticalStatus: 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: High6 findings

Severity: HighStatus: OpenSQ-TOOL-EXFIL-DIRECTIVE

Asks the AI model to pass conversation data or secrets

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.

Severity: HighStatus: OpenSQ-TOOL-EXFIL-DIRECTIVE

Asks the AI model to pass conversation data or secrets

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.

Severity: HighStatus: OpenSQ-TOOL-EXFIL-DIRECTIVE

Asks the AI model to pass conversation data or secrets

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.

Severity: HighStatus: OpenSQ-TOOL-EXFIL-DIRECTIVE

Asks the AI model to pass conversation data or secrets

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.

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: Medium2 findings

Severity: MediumStatus: OpenSQ-TOOL-PREFERENCE-MANIPULATION

Pressures the AI model to prefer this tool

Model-facing text pressures the AI model to always choose this tool or avoid others.

First seen · Last seen

Suggested fix: Describe the tool's function neutrally.

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: Low3 findings

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-LENGTH-ANOMALY

Unusually long model-facing text

Model-facing text is unusually long, which consumes context and leaves room to hide content.

First seen · Last seen

Suggested fix: Shorten descriptions; move long documentation out of model-facing fields.

Severity: LowStatus: OpenSQ-REPO-MISSING

No source repository linked

No source repository is linked in the registry entry.

First seen · Last seen

Suggested fix: Add a repository to server.json.

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.

How Squatch scans servers