ClawHub
Back to skill

Security audit

Search and Book Flights

Security checks for vulnerabilities and agentic risk

Overview

This travel-booking skill is high touch because it uses email and can lead to paid bookings, but its behavior is disclosed, user-directed, and aligned with its purpose.

Install only if you are comfortable letting your agent use your email for BonBook travel messages and, when you choose, assisting with account setup, calendar sync, and booking confirmations. Keep payment and identity-document entry human-approved unless you intentionally grant the agent that access.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · skill.md (reported line 65)May include surrounding context.

  1. WEBSITE CHANNEL (optional): Account setup and payment occur on bonbook.co website (not email). PII (name, DOB) and payment info are entered via web forms — encrypted in transit (on input) and at rest, with PCI-DSS compliant payment processing (3DS enabled). Form completion by agent requires explicit human approval.

This skill does NOT store, transmit, or access credentials.

text

## CONSENT

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The manifest description says 'One message, and done,' which describes activation in a very broad, everyday way without defining specific trigger phrases or constraints. In a markdown/manifest context, this kind of generic invocation language can overlap with common user requests and does not clarify when the skill should or should not be used.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.