ClawHub
Back to skill

Security audit

AANA Purchase Booking Guardrail Skill

Security checks across malware telemetry and agentic risk

Overview

This skill is an instruction-only guardrail that tells agents to get explicit approval before purchases or bookings and to redact sensitive payment data.

Safe to install as a guardrail, with normal caution for any separate tools that can actually spend money, book travel, change subscriptions, or access payment data. Keep those tools permissioned separately and require final confirmation of the exact cost, terms, and payment method before any binding action.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
4. Check authorization: confirm the user explicitly approved this exact action and cost.
5. Check payment privacy: do not expose full payment numbers, bank details, credentials, or unnecessary account data.
6. Check reversibility: prefer cart, quote, draft, hold, or review screen before final submission.
7. Check scope: do not add extras, warranties, insurance, upsells, tips, donations, seats, bags, or subscriptions without approval.
8. Choose action: accept, revise, ask, defer, refuse, or route to human review.

## Required Pre-Flight Checks
Confidence
75% confidence
Finding
without approval

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
Prefer:

- compare options before choosing,
- prepare a cart without checking out,
- hold or reserve only when the terms are clear,
- ask the user to complete payment directly,
- use a review screen before final confirmation,
Confidence
75% confidence
Finding
without checking

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
- If final commitment facts are incomplete, ask.
- If the draft includes unapproved add-ons, recurring terms, fees, or payment details, revise.
- If the action is high-value, non-refundable, legally binding, or for someone else, defer or require explicit approval.
- If the request would expose payment secrets, bypass consent, misrepresent terms, or spend money without approval, refuse and explain briefly.
- If a checker is unavailable or untrusted, use manual purchase and booking review.

## Output Pattern
Confidence
75% confidence
Finding
without approval

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
- If final commitment facts are incomplete, ask.
- If the draft includes unapproved add-ons, recurring terms, fees, or payment details, revise.
- If the action is high-value, non-refundable, legally binding, or for someone else, defer or require explicit approval.
- If the request would expose payment secrets, bypass consent, misrepresent terms, or spend money without approval, refuse and explain briefly.
- If a checker is unavailable or untrusted, use manual purchase and booking review.

## Output Pattern
Confidence
85% confidence
Finding
bypass consent

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.