Back to skill

Security audit

print-helper

Security checks for vulnerabilities and agentic risk

Overview

The skill is marked suspicious because scanners report that duplex printing may ignore the selected printer and page range, potentially sending the full document to the default printer.

Review the duplex printer and page-selection behavior before installing, especially if documents may contain sensitive pages or the default printer is shared. The scan was partial: it reports a missing referenced path, so the evidence is incomplete.

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
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The security-relevant mismatch is that duplex printing ignores the selected printer and page range, instead printing the entire document to the default printer. In a local printing skill, this can disclose sensitive pages or send confidential documents to a shared or unintended printer; the unimplemented copy count and limited format support are primarily functional defects.

Content

No source excerpt is available for this finding.

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env, shell.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/print_pdf.py (reported line 37)May include surrounding context.

python
cmd.append(filepath)

    try:
        subprocess.run(cmd, check=True, capture_output=True, timeout=120)
        return True, f"Sent to printer: {filepath} (pages={pages or 'all'})"
    except subprocess.TimeoutExpired:
        return False, "Print timeout"