Severity: HighStatus: OpenSQ-RESOURCE-SENSITIVE-URI
Resource at a sensitive system or credential path
A resource or resource template points at a sensitive system, key or credential location.
First seen · Last seen
MCP Endpoint Lint - handshake, tool schemas, JSON-RPC errors
dev.workers.pathwren.www/mcp-endpoint-lint
Findings
Detected by Squatch rules from the server's metadata and protocol behavior. Latest completed scan: .
Severity: High4 findings
Suggested fix: Do not expose credential or system configuration paths as resources.
Severity: HighStatus: OpenSQ-RESOURCE-INJECTION
Resource metadata contains directives to the AI model
A resource's metadata contains instructions addressed to the AI model.
First seen · Last seen
Suggested fix: Describe resources neutrally.
Severity: HighStatus: OpenSQ-TOOL-SENSITIVE-PATH-REFERENCE
References credential or key locations
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.
Severity: HighStatus: 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: Medium5 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-PROMPT-INJECTION
Prompt metadata contains directives to the AI model
A prompt's description or arguments contain instructions addressed to the AI model.
First seen · Last seen
Suggested fix: Describe prompts 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: 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: Low2 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-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.