ClawHub
Back to skill

Security audit

Aerobase Flight Awards

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently provides an Aerobase API integration for flight award searches and alerts, with disclosed API-key use and no hidden local execution.

Before installing, understand that the skill will use your Aerobase API key to search award availability and can create, deactivate, or delete Aerobase alerts when asked. Use clear instructions for alert changes and avoid sharing travel-account passwords, OTPs, cookies, or loyalty logins.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • 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)

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
84% confidence
Finding

The skill exposes state-changing alert management endpoints, including DELETE, without any documented requirement for explicit user confirmation, ownership checks, or guardrails on destructive operations. In an agent setting, this can enable unintended or prompt-induced deletion/modification of user alerts if the model acts on ambiguous or adversarial instructions.

Content

Scanner excerpt · SKILL.md (reported line 72)May include surrounding context.

md
- **POST /api/awards/alerts** — create alert for a route/date band.
- **GET /api/awards/alerts** — list user alerts.
- **PATCH /api/awards/alerts/{id}** — activate/deactivate alert.
- **DELETE /api/awards/alerts/{id}** — remove alert.

## Trip detail

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 25)May include surrounding context.

md
- Base URL: `https://aerobase.app`
- Required env var: `AEROBASE_API_KEY`
- Auth header (preferred): `Authorization: Bearer ${AEROBASE_API_KEY}`
- Never ask users for passwords, OTPs, cookies, or third-party logins.
- Never print raw API keys in output; redact as `sk_live_***`.

### Request rules

Static analysis

No suspicious patterns detected.