Back to skill

Security audit

Geomanic

Security checks for vulnerabilities and agentic risk

Overview

This skill appears to do what it says: connect OpenClaw to Geomanic travel data, including reading and changing sensitive location records.

Install this only if you want OpenClaw to access your Geomanic GPS history. Treat GEOMANIC_TOKEN like a password, avoid exposing raw location results unnecessarily, and confirm the exact waypoint and intended change before create, update, or delete actions.

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
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 (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The markdown file lists a delete_waypoint tool with no accompanying warning about deletion impact, confirmation expectations, or recoverability. Because waypoint deletion can affect user data and system integrity, the skill description should explicitly disclose that this operation removes stored data and whether it can be undone.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs the agent to send a bearer token and highly sensitive GPS/location data to a remote service without an explicit privacy notice or data-sharing warning. Because travel history can reveal home/work patterns and movements, omission of clear disclosure and consent guidance creates a meaningful privacy and credential-handling risk.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
91% confidence
Finding

This skill explicitly directs use of curl to POST data to an external endpoint with an Authorization bearer token, which is a genuine external transmission path. In context this is expected functionality, but it still creates security exposure because secrets and sensitive waypoint/travel data leave the local environment and may be sent in response to unsafe prompts if the agent lacks guardrails.

Content

Scanner excerpt · SKILL.md (reported line 20)May include surrounding context.

Use curl via the exec tool to send JSON-RPC requests to https://geomanic.com/api/v1/mcp:

bash
curl -s -X POST https://geomanic.com/api/v1/mcp \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $GEOMANIC_TOKEN" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"TOOL_NAME","arguments":{...}}}'

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill exposes mutation and deletion operations for waypoint data but provides no guidance to require explicit user confirmation before creating, modifying, or deleting records. In an agent setting, this increases the risk of accidental or prompt-induced destructive actions against sensitive travel history, especially because location records are difficult to reconstruct once altered or removed.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.