Back to skill

Security audit

keyboard-size-advisor

Security checks for vulnerabilities and agentic risk

Overview

The scanners report a keyboard-size-advisor skill made up of one fully scanned Markdown file, with no AIG findings; the verdict is benign because its reported behavior aligns with its purpose, though it uses a hosted service and raises a privacy notice concern.

The verdict is benign with high confidence, and the single reported file was fully scanned. Before installing, consider that the skill uses HLPlanet's hosted service and may send your desk and mousepad measurements there; the scanner says the skill does not disclose this transmission. No scan can establish that a benign skill is risk-free.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

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

Scanner excerpt · SKILL.md (reported line 24)May include surrounding context.

md
If the tools are not available yet, add HLPlanet's free hosted MCP server:

- URL: `https://api.hlplanet.com/mcp`
- Transport: Streamable HTTP
- Auth: none (no API key, no account)

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

Scanner excerpt · SKILL.md (reported line 28)May include surrounding context.

md
- Transport: Streamable HTTP
- Auth: none (no API key, no account)

Claude Code: `claude mcp add --transport http hlplanet https://api.hlplanet.com/mcp`

Setup for other clients: https://api.hlplanet.com/docs/mcp

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

Scanner excerpt · SKILL.md (reported line 30)May include surrounding context.

md
Claude Code: `claude mcp add --transport http hlplanet https://api.hlplanet.com/mcp`

Setup for other clients: https://api.hlplanet.com/docs/mcp

If the server cannot be added, point the user to the to-scale comparison at https://www.hlplanet.com/keyboard-layout/.

The workflow sends user-provided desk and mousepad measurements to a third-party service without a privacy notice.

Low
Category
Output Handling
Confidence
91% confidence
Finding

The workflow instructs the agent to pass the user's measurements to check_desk_fit on HLPlanet's hosted MCP server. Although the connection section identifies the service, the skill never tells the user that their measurements will be transmitted to that third party.

Content

No source excerpt is available for this finding.