ClawHub
Back to skill

Security audit

Flight Tracker

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Brazil-focused flight-checking helper, but it currently performs only basic travel-site page checks rather than real fare tracking.

Install only if you are comfortable with scheduled flight-site checks and possible WhatsApp delivery of your travel search details. Treat the current output as connectivity diagnostics, not confirmed flight recommendations or fare matches, unless the skill is updated to parse real flight data.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill explicitly states that results are sent via WhatsApp, which involves transmitting data to a third-party service, but it does not warn the user about that external disclosure or any privacy implications. Even if the data appears low sensitivity, travel searches can reveal itinerary preferences, location patterns, and contact linkage, so silent transmission reduces informed consent and creates avoidable privacy risk.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The script advertises automated flight searching with specific fare and itinerary constraints, but it only performs basic HTTP GET requests and records page load status, content length, and errors. This is a security-relevant integrity issue because downstream automation or users may rely on the output as if it contains real search results, leading to false decisions and unsafe trust in fabricated or incomplete data.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The comments and status output state that the script runs scanners and saves flight search results, but the stored data is only connectivity diagnostics from airline and aggregator landing pages. In an agent skill that is supposed to send reports on a schedule, this discrepancy can mislead operators or downstream systems into treating non-results as validated travel recommendations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The natural-language content of the skill, including its description and operating details, is presented exclusively in Portuguese. Under the language/locale policy, forcing a single language without user opt-in or a documented regional justification can be a policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The Google Flights request hard-codes hl=pt-BR, which imposes a specific language/locale in the skill's behavior. The file does not offer a user opt-in or explain why Portuguese is required, so this is a natural-language locale policy issue rather than a technical bug.

Content

No source excerpt is available for this finding.