Severity: CriticalStatus: OpenSQ-TOOL-CONCEALMENT
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
io.github.cyanheads/secedgar-mcp-server
io.github.cyanheads/secedgar-mcp-server
Findings
Detected by Squatch rules from the server's metadata and protocol behavior. Latest completed scan: .
Severity: Critical2 findings
Suggested fix: Remove any wording that asks the model to act silently or withhold information from the user.
Severity: CriticalStatus: 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: High5 findings
Severity: HighStatus: 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: HighStatus: OpenSQ-TOOL-TITLE-EFFECT-MISMATCH
Display title describes a lower-impact action than the 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.
Severity: HighStatus: OpenSQ-TOOL-CONCEALMENT
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
Suggested fix: Remove any wording that asks the model to act silently or withhold information from the user.
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: Medium4 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-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: MediumStatus: 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: MediumStatus: OpenSQ-TOOL-OVERLY-BROAD
Runs arbitrary code with open-world access
The tool runs code, commands or queries supplied at call time and does not declare a closed-world scope.
First seen · Last seen
Suggested fix: Narrow the tool to specific operations, or declare and enforce a closed-world sandbox.
Severity: Low2 findings
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-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.
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.