Back to skill

Security audit

Motor PID Tuner

Security checks for vulnerabilities and agentic risk

Overview

The skill is marked suspicious because scanners found two confirmed motor-control analysis or code-generation correctness concerns that could lead to unsafe tuning decisions; they did not report clear malicious behavior.

Consider avoiding installation for safety-critical motor tuning unless the gain conversion and stability-analysis concerns are independently reviewed and resolved. The scan completed across all four components, but its findings do not establish that the skill is safe in every use.

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
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

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

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.

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

The code generator documents digital-domain gains but discretizes them again.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

generate_c_code documents its gains as digital-domain values but multiplies Ki by Ts and divides Kd by Ts before emitting C. A caller following that contract would discretize twice, weakening integral action and greatly amplifying derivative action; if deployed to a motor controller, the generated gains could cause severe noise amplification, saturation, or unstable motion.

Content

No source excerpt is available for this finding.

Cascaded position-loop stability analysis evaluates a different transfer function from the one documented.

Medium
Category
Excessive Agency
Confidence
100% confidence
Finding

The documented cascaded position-loop denominator is s(s + omega_s), requiring coefficients [1, omega_s, 0], but the implementation uses [1, omega_s, 0, 0], adding an unintended integrator. Consequently, crossover frequencies and stability margins describe a different plant, undermining safety-relevant tuning decisions and potentially contributing to unsafe motor behavior if the reported assessment is trusted.

Content

No source excerpt is available for this finding.

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.