Back to skill

Security audit

tire-pressure-coach

Security checks for vulnerabilities and agentic risk

Overview

This is a local tire-maintenance helper that stores a local JSON log; its docs overstate a few features, but I found no hidden network access, credential use, or unsafe persistence.

Before installing, know that the tool saves vehicle names, placard pressures, pressure checks, and tread measurements in a local JSON file. Treat it as educational support only: verify pressures against your door placard or manual, and do not rely on it for advanced load/speed calculations or TPMS diagnostics beyond the simple guidance shown in the docs.

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)

Tp4

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

The skill description materially overstates and misstates behavior: it claims TPMS decoding and load/speed corrections, while also omitting disclosure that it stores maintenance history locally. In a safety-adjacent automotive context, this mismatch is dangerous because users may rely on absent safety logic or unknowingly permit local data persistence, leading to incorrect maintenance decisions and weakened trust boundaries.

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.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding

The skill declares no tool scope or permissions, yet its documented behavior persists data to a local JSON file and supports logging. This creates an undeclared file read/write capability boundary, which can surprise hosts, bypass least-privilege expectations, and allow unintended access to local filesystem data if the runtime auto-grants capabilities based on implementation rather than explicit manifest policy.

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.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

This code writes vehicle and tire-history data to disk, which affects user data persistence. Although the module docstring mentions the store file, the write function itself has no confirmation, logging, or inline warning, so users invoking commands may not realize new or updated records are being saved automatically.

Content

No source excerpt is available for this finding.