T05 · Unauthorized Access and Privilege Escalation
Warning
- Location
SKILL.md:18- Finding
Broad Remote MCP Tool Access Without Default Least-Privilege Filtering
- Content
View full analysis
- Remediation
View remediation
Security audit
Latitude MCP
Security checks for vulnerabilities and agentic risk
Overview
This skill clearly describes a Latitude MCP integration, but it defaults to broad OAuth-backed access that can read and manage sensitive Latitude workspace resources.
Review this before installing on a production Latitude organization. Use the least-privileged Latitude account or organization you can, inspect the exposed tools with the probe command, add a toolFilter for routine use, and revoke or logout when the agent no longer needs access.
Vulnerability Patterns
- Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
- Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
- Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
- Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
- Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)
Vulnerability Patterns
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (5)
External Transmission
Medium
- Category
- Data Exfiltration
- Confidence
- 50% confidence
- Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
- Content
md [Latitude](https://latitude.so) is an open-source LLM observability and evaluation platform. Its MCP server is a remote, OAuth-authenticated, streamable HTTP [Model Context Protocol](https://modelcontextprotocol.io) server at `https://api.latitude.so/v1/mcp`. Connecting it lets an OpenClaw agent read and manage your Latitude workspace directly: projects, members, API keys, traces, spans, issues, annotations,
External Transmission
Medium
- Category
- Data Exfiltration
- Confidence
- 50% confidence
- Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
- Content
md [Latitude](https://latitude.so) is an open-source LLM observability and evaluation platform. Its MCP server is a remote, OAuth-authenticated, streamable HTTP [Model Context Protocol](https://modelcontextprotocol.io) server at `https://api.latitude.so/v1/mcp`. Connecting it lets an OpenClaw agent read and manage your Latitude workspace directly: projects, members, API keys, traces, spans, issues, annotations,
External Transmission
Medium
- Category
- Data Exfiltration
- Confidence
- 50% confidence
- Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
- Content
md [Latitude](https://latitude.so) is an open-source LLM observability and evaluation platform. Its MCP server is a remote, OAuth-authenticated, streamable HTTP [Model Context Protocol](https://modelcontextprotocol.io) server at `https://api.latitude.so/v1/mcp`. Connecting it lets an OpenClaw agent read and manage your Latitude workspace directly: projects, members, API keys, traces, spans, issues, annotations,
External Transmission
Medium
- Category
- Data Exfiltration
- Confidence
- 50% confidence
- Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
- Content
md [Latitude](https://latitude.so) is an open-source LLM observability and evaluation platform. Its MCP server is a remote, OAuth-authenticated, streamable HTTP [Model Context Protocol](https://modelcontextprotocol.io) server at `https://api.latitude.so/v1/mcp`. Connecting it lets an OpenClaw agent read and manage your Latitude workspace directly: projects, members, API keys, traces, spans, issues, annotations,
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The skill explicitly states that connecting the MCP server allows the agent to read and manage a broad set of Latitude workspace resources, including highly sensitive assets such as members and API keys, but it does not present a prominent warning about the scope of access or the risks of granting it. In this context, users may authorize the integration without understanding that the agent can perform management actions across sensitive workspace data, increasing the chance of over-privileged use and accidental exposure or modification.
- Content