Back to skill

Security audit

excitation-signal-design

Security checks for vulnerabilities and agentic risk

Overview

This is a plain instructional control-systems skill with no code execution, but real equipment tests require safe operating limits and supervision.

Install only if you want control-systems step-test guidance. For real equipment, verify safe operating ranges, use small bounded inputs, confirm supervision and emergency stop capability, and avoid production or safety-critical systems without a risk assessment.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill instructs users to apply a step input to an unknown system without any explicit safety warning, pre-checks, or operational limits. In control systems, abrupt input changes can cause overshoot, actuator saturation, equipment stress, or unsafe process excursions, so omission of cautions can lead users to perform hazardous tests inappropriately.

Content

No source excerpt is available for this finding.