Back to skill

Security audit

electrical-circuit-detective

Security checks for vulnerabilities and agentic risk

Overview

The skill provides local electrical troubleshooting and optional circuit logging, with no evidence of hidden access or data transmission.

Use the calculations as preliminary estimates and verify appliance input watts and matched names. Have a qualified electrician handle wiring repairs. Optional mapping keeps household details in plaintext at ~/.circuit_map.json; avoid sensitive notes and remember that reusing a label replaces its entry.

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
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

The main diagnostic functions match the description, and the appliance database supports load calculation. However, the separate map subcommand adds user-data collection and persistent filesystem access not disclosed in the declared purpose. This is an additional user-facing capability, rather than merely an implementation detail of the declared diagnostics. No network access or command execution is present.

Content

No source excerpt is available for this finding.

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.