Security audit

Waze

Security checks for vulnerabilities and agentic risk

Overview

This Waze-link skill does what it says, but it asks agents to read broad profile files and automatically send location context to an external search service without a clear consent step.

Review this skill before installing if your workspace or agenda contains sensitive location information. It should be safer if limited to explicit user requests, exact approved profile fields, and confirmation before sending city, state, destination, or calendar-location details to Tavily.

A.I.G

Vulnerability Patterns

Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
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

Findings (1)

T05 · Unauthorized Access and Privilege Escalation

Warning

Location: SKILL.md:41
Finding: Overbroad Workspace Profile Access and External Location Disclosure
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The activation scope is broad enough to trigger on routine mentions of destinations, routes, or agenda items, which can cause the skill to run without clear user intent. In this skill, that matters because activation can lead to location inference from profile files and possible downstream external lookup for vague destinations, increasing the chance of unnecessary processing of sensitive location data.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill directs automatic processing of agenda event locations and, for vague locations, external search based on the user's city, without informing the user or requesting consent. This can expose sensitive calendar and location context to external services and may surprise users who did not explicitly ask for navigation assistance.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.